diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..21d35c05a713d3cfe2805c169503bc55e4d43290 --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +base_model: [] +library_name: transformers +tags: +- mergekit +- merge + +--- +# test-model-24 + +This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). + +## Merge Details +### Merge Method + +This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022 as a base. + +### Models Merged + +The following models were included in the merge: +* /workspace/magnex +* /workspace/cache/models--bruhzair--ignore-merge-17/snapshots/bd0af76a6bc4d9ae4bab5fa6b50e6545e6f3fd4f + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +models: + - model: /workspace/magnex + parameters: + select_topk: 0.16 + - model: /workspace/cache/models--bruhzair--ignore-merge-17/snapshots/bd0af76a6bc4d9ae4bab5fa6b50e6545e6f3fd4f + parameters: + select_topk: 0.16 + - model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022 + parameters: + select_topk: 0.16 +base_model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022 +merge_method: sce +tokenizer: + source: base +dtype: float32 +out_dtype: bfloat16 +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..87e0218883826e7b479fce29aacff5742cb0272f --- /dev/null +++ b/config.json @@ -0,0 +1,37 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 120, + "num_key_value_heads": 8, + "pad_token_id": 128004, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3", + "unsloth_fixed": true, + "use_cache": false, + "vocab_size": 128256 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000000000000000000000000000000000000..91b0c9b7a916da4cd359a7117252dd37e599de3e --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,16 @@ +models: + - model: /workspace/magnex + parameters: + select_topk: 0.16 + - model: /workspace/cache/models--bruhzair--ignore-merge-17/snapshots/bd0af76a6bc4d9ae4bab5fa6b50e6545e6f3fd4f + parameters: + select_topk: 0.16 + - model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022 + parameters: + select_topk: 0.16 +base_model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022 +merge_method: sce +tokenizer: + source: base +dtype: float32 +out_dtype: bfloat16 \ No newline at end of file diff --git a/model-00001-of-00044.safetensors b/model-00001-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8abd42e290f784b1570f471b5273eb4932a9b1c2 --- /dev/null +++ b/model-00001-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b6e0c861a36424c39852f31ddb4283fa0b416796c7e6eb01aa5444fc058d2e +size 3875621032 diff --git a/model-00002-of-00044.safetensors b/model-00002-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a9a03cd9125751f6e9e0705144f3cb636b403fa4 --- /dev/null +++ b/model-00002-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb4edfb89eff010457d6a6d5de421252cd834d5b040c148dd390f93cae9e28f3 +size 4618012992 diff --git a/model-00003-of-00044.safetensors b/model-00003-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4708ae233814f01173373665a2f23c9c58d67063 --- /dev/null +++ b/model-00003-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6e6b1b48fb03255ade586008ff6ac986406a1be5f1f2e7165067ae9ea036b74 +size 4550837664 diff --git a/model-00004-of-00044.safetensors b/model-00004-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..33f8545f91e4b758714b9d69be58cb43620b9313 --- /dev/null +++ b/model-00004-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af5d33f19b407b5728db3f3e5119d53d300bc95330979c670a02d6abd9e7c12 +size 4546726216 diff --git a/model-00005-of-00044.safetensors b/model-00005-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e76df04006261b3df9b5666dfd2676de6f20dad3 --- /dev/null +++ b/model-00005-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eabb6f05298bbecbf94a9f83df4b6fbc5aea89882f4758b75e0e45b7d0c11311 +size 4664134432 diff --git a/model-00006-of-00044.safetensors b/model-00006-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ceb450a317540602d2f2d560baa1fd5df0aac9b2 --- /dev/null +++ b/model-00006-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:656b5e6e950c64a9cc6ecd7b04a003f3bddb9ccdf2d003043bbdf6c82ac01233 +size 4966174304 diff --git a/model-00007-of-00044.safetensors b/model-00007-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0936fc2308767797214620f45dad456cc5614936 --- /dev/null +++ b/model-00007-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:141fe690d88154bfbf0cea31ab64e042f9389e7318e45425a67cda5fd2f5c035 +size 4899031360 diff --git a/model-00008-of-00044.safetensors b/model-00008-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a562384d0e4a5ce362d2583d223d64a661f97f83 --- /dev/null +++ b/model-00008-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f31adcfb2bf8fc5622de33e19504ce91253c88193640f6baf2882a3cf47d8614 +size 4865511008 diff --git a/model-00009-of-00044.safetensors b/model-00009-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..66cd3b249c3962b4da48344b432c7980e23c797c --- /dev/null +++ b/model-00009-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6407102fff7b91daccfba0bfea87dddad0e32b93794b12667b60b8b5dc40935 +size 4999678752 diff --git a/model-00010-of-00044.safetensors b/model-00010-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb5149bcf5fcf00c1e9682ebc572bf7beaddc1cb --- /dev/null +++ b/model-00010-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:672f998bd2dac6bfb670f9654a9f4e8d2e58b1238bbe38fe46741979cbce55e3 +size 4899047848 diff --git a/model-00011-of-00044.safetensors b/model-00011-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..852c64f0b08a9b09c4d78471d1e114a487bfc885 --- /dev/null +++ b/model-00011-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73f0eb7efca425f3718d8e88a14eb507ec54c71674b8c9f5ea3e4f79c9d3e438 +size 4915842968 diff --git a/model-00012-of-00044.safetensors b/model-00012-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a92ed25eceec469ec5f422d9bf75e99b4c986b38 --- /dev/null +++ b/model-00012-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f873e53b971f9ed0158daede9c51efde5495e22733b237abe1c11f241fe98d3c +size 4815128888 diff --git a/model-00013-of-00044.safetensors b/model-00013-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fdc271716acd2537fdc02b311272d118e1285db9 --- /dev/null +++ b/model-00013-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bd52529712612b9ffbd31779c3f3f8606f2ed3537c69c744bbe3fd173e35ac9 +size 4697721360 diff --git a/model-00014-of-00044.safetensors b/model-00014-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..503e69c51da588abe1c338e162880f7a57bbfa00 --- /dev/null +++ b/model-00014-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddf5a3e2eab0d31807f5d65dfa10e0c9673e8fff9e3555df10ff719abf696836 +size 4664184616 diff --git a/model-00015-of-00044.safetensors b/model-00015-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..957076df1d21c77ad75e71a29e5eb34f518a36b3 --- /dev/null +++ b/model-00015-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:688dafaa11ec608a0b4769a42f774584b1903c96c1e69506561d78dc5f23fe78 +size 4781541232 diff --git a/model-00016-of-00044.safetensors b/model-00016-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3bdedf4efbe2e21b1704fd61cc7b326f05146e2d --- /dev/null +++ b/model-00016-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bd327d1f6e0db72951b3019d97e07c12686f2ed393aa5af73f20adc3c322e23 +size 4546759880 diff --git a/model-00017-of-00044.safetensors b/model-00017-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58732db7a51b54f4d2b6b7fb760d91fc37d6c98c --- /dev/null +++ b/model-00017-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445dc4f798a1e8863cb792cd483cb2d1942efa442d5950bbdc3b609e89597fef +size 4848733760 diff --git a/model-00018-of-00044.safetensors b/model-00018-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..26ad9159c049c97e54191aac46978a41bf6c1d86 --- /dev/null +++ b/model-00018-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eace80618b3ea03afd3ba60048878751eaa034d1638f0bc2e988c650227ede30 +size 4798335048 diff --git a/model-00019-of-00044.safetensors b/model-00019-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6658fc0bc535a953a46f15547013bce7a63f8399 --- /dev/null +++ b/model-00019-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2baeb46c5e237cce6ce97ffb39bbf0108f027f7241d9c8073aef673ae68f3a0c +size 4647390072 diff --git a/model-00020-of-00044.safetensors b/model-00020-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ecd7a875f5a4917da6eaa955104343dca8eb0821 --- /dev/null +++ b/model-00020-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6ed9f09c218e1edecfcd0dc734e4a7f07dd3d0a681b12afd738eacd334d865d +size 4982951616 diff --git a/model-00021-of-00044.safetensors b/model-00021-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ea9e7e8fdbf2d49ce0c9d4f0ee0bc14f95136e9 --- /dev/null +++ b/model-00021-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06cc18971059ce85479bc62423c143e1bcb8ac0defee5fe76de372ab739c64c +size 4546709688 diff --git a/model-00022-of-00044.safetensors b/model-00022-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2c707ea2c9f45a8e60daadc5cb608c127f9ac451 --- /dev/null +++ b/model-00022-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be9e049dcc44df421b6f9649e707038d35820759cff5adcb18828b9a9199ee0 +size 4949363936 diff --git a/model-00023-of-00044.safetensors b/model-00023-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8cabb51ddb6efd5555df9cdaa6468b57e73ba67a --- /dev/null +++ b/model-00023-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b14ed2b23b4d8ee765a43a0f130ba994fc39c765afccad1bbdcad6cfafc6cd90 +size 4664183920 diff --git a/model-00024-of-00044.safetensors b/model-00024-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a5dfcf4e0b97f83343e69d2ada402b1773e4dd91 --- /dev/null +++ b/model-00024-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ea97d521a753810fb3830d5ac1a9ddc1ac79eadfd32031e67584e3dea6ebb7d +size 4563454024 diff --git a/model-00025-of-00044.safetensors b/model-00025-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3b3f51d10328b1a87e2cc754a7b7f5fcef80a455 --- /dev/null +++ b/model-00025-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87b4462c05774af9317c78946ef9895a9042a9058e2ead339bbe1f258b71a41e +size 4932619592 diff --git a/model-00026-of-00044.safetensors b/model-00026-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5ec8a7c2088cf4945876302fe3ee51728c4e068f --- /dev/null +++ b/model-00026-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5acaf0a5cdf2fd85907f515ccc673870875401130cc94a1d71b2f17537eed3c2 +size 4798385264 diff --git a/model-00027-of-00044.safetensors b/model-00027-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a769d826520cfd749fb05dbd6f3a2b42e09d22f --- /dev/null +++ b/model-00027-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a9d2a3a126a20d523f9b360c0c6e5e7387a7746ded65d0badb494da5a6b26f +size 4899047840 diff --git a/model-00028-of-00044.safetensors b/model-00028-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..081dbcb540f391308f0ccd4200feb72ff084e91c --- /dev/null +++ b/model-00028-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cf41a4fce7bf2f7311a9f4f4a76f32446305059154faa4ec03a70c566a8a9c9 +size 4915826464 diff --git a/model-00029-of-00044.safetensors b/model-00029-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e481ccaa6bacbb038721fef7f30b568ca4d31d0 --- /dev/null +++ b/model-00029-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:156611589021dd0531c082c53e720d1d7168d873e420afd098403334e5a7080e +size 4949346728 diff --git a/model-00030-of-00044.safetensors b/model-00030-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..50edfb70df530eeb5c1bbc39252dc92ee33be1fb --- /dev/null +++ b/model-00030-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d4e12eba570682d501a7cecdc725d434d2fec9ec45078431c4d7ae6698b1389 +size 4798401152 diff --git a/model-00031-of-00044.safetensors b/model-00031-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5ddf926dbb53b3769d7e4e6f3b72fbd15dc1922e --- /dev/null +++ b/model-00031-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b4199d8719e9b17ff5e007b42e98470df38da96248da3ac3d79b464b0ba9412 +size 4731293848 diff --git a/model-00032-of-00044.safetensors b/model-00032-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a2eb6c321d617b41b23c5021096025a160238aa3 --- /dev/null +++ b/model-00032-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9346a439badd270bbbcb902205974106cb7658b07578e0989f1b7529d3024355 +size 4647323376 diff --git a/model-00033-of-00044.safetensors b/model-00033-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db93058f969df563aab0b8d05a34998eff85c71a --- /dev/null +++ b/model-00033-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85d6b0db574b429ff26f75b754519aa3c0a196f93e4bfc009c81a9a47825996 +size 4932635488 diff --git a/model-00034-of-00044.safetensors b/model-00034-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..00544547a5e0a950a93414eb3794be0707961e54 --- /dev/null +++ b/model-00034-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08b7b355aa23217010072c5ed1a96f885294704be41a2f85ca43e01ecca75c1f +size 4563521344 diff --git a/model-00035-of-00044.safetensors b/model-00035-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..adf295c71a63897aab88c099d866221d453ed88b --- /dev/null +++ b/model-00035-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ad9b777079d2a0e0c14b92167da5c4546717de13e014784b1f151462bc17933 +size 4999628528 diff --git a/model-00036-of-00044.safetensors b/model-00036-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b495d3ffdc43e4e0570e4bc1fd9144aad60e0d35 --- /dev/null +++ b/model-00036-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcbf1aa401f57d944efc6765f1f542936558b661043de09ab71afa4ee9ad72c6 +size 4815195576 diff --git a/model-00037-of-00044.safetensors b/model-00037-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..37ee6b1f1611860dedd2af1fe9240a550fb3145d --- /dev/null +++ b/model-00037-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b3cf472e3c31378ea70b1fff094f41afe9de420d96a821bdbfa82d5c200926d +size 4680977760 diff --git a/model-00038-of-00044.safetensors b/model-00038-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6f70840c15a5dbc63033a9f6b40fd175922d99a7 --- /dev/null +++ b/model-00038-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9641dc0ef7b0f945a156a391ce4fcdeec9a8f1d70d0b0acde11752f060447c85 +size 4647290376 diff --git a/model-00039-of-00044.safetensors b/model-00039-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a5b33a27635b3fb385e89c5b055e9c84d82e3a9c --- /dev/null +++ b/model-00039-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c2d106af61a8136175ba01c5fd936065bfc100a63acc461cad9ecc5015ba454 +size 4966190760 diff --git a/model-00040-of-00044.safetensors b/model-00040-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7bc0ce3c64e2c2492bdd88f81875abae68fc00db --- /dev/null +++ b/model-00040-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdb201cea295248c53f6f6b3f3c4858b0ce9492faea59f189d03d2a5634a5a8a +size 4546759912 diff --git a/model-00041-of-00044.safetensors b/model-00041-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..22642d3b1e39e08177afc693da611caa193da475 --- /dev/null +++ b/model-00041-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75798f0f0957cd1c5593a7cb476491af7779a039cea8c64a17b585024b110a36 +size 4982834688 diff --git a/model-00042-of-00044.safetensors b/model-00042-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..15f44342aacfc5b13f16ff276374c361e3eafd24 --- /dev/null +++ b/model-00042-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce0fe04035e05abb3b014bbf6a647a8b1b9613531fc78539c0c16a546857f19 +size 4781691832 diff --git a/model-00043-of-00044.safetensors b/model-00043-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..23efccc28c57a63cad5879573c2511b69a88f092 --- /dev/null +++ b/model-00043-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b2a88a579e929fa77f2e9b954b1371b133a91b9889fd3735e86f483b12be2fe +size 4865476672 diff --git a/model-00044-of-00044.safetensors b/model-00044-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ba5f57eb036ad36dec05013223d237fff3ec9348 --- /dev/null +++ b/model-00044-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bd3a3e8ac662788da37418a740f41ea2dd6ea9fad728ff58aad96917aa52c49 +size 4798368736 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..caf20b28acdebf33ab4e49809c36860e0ef615a0 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00044.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00044.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00044.safetensors", "lm_head.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.101.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.embed_tokens.weight": "model-00003-of-00044.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.104.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.105.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.102.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.108.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.112.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.11.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.116.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.115.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.118.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.119.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.117.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.15.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.17.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.27.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.26.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.24.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.28.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.29.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.30.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.3.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.34.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.33.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.35.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.31.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.38.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.41.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.39.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.48.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.46.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.53.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.6.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.61.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.63.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.62.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.60.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.69.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.70.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.68.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.71.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.72.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.76.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.78.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.75.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.79.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.80.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.81.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.83.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.84.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.86.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.82.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.91.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.92.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.90.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.93.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.9.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.input_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.99.input_layernorm.weight": "model-00044-of-00044.safetensors", "model.norm.weight": "model-00044-of-00044.safetensors", "model.layers.97.input_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00044-of-00044.safetensors"}} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1c8301f15aa999eb01aa7bbc2da2dd4ca261b5cd --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2066 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "padding_side": "left", + "tokenizer_class": "PreTrainedTokenizer", + "unk_token": null +}