Upload folder using huggingface_hub

README.md

@@ -0,0 +1,30 @@
+---
+license: apache-2.0
+tags:
+- trl
+- orpo
+- generated_from_trainer
+- mlx
+base_model: mistral-community/Mixtral-8x22B-v0.1
+datasets:
+- argilla/distilabel-capybara-dpo-7k-binarized
+model-index:
+- name: zephyr-orpo-141b-A35b-v0.1
+  results: []
+---
+
+# mlx-community/zephyr-orpo-141b-A35b-v0.1-4bit
+This model was converted to MLX format from [`HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1`]().
+Refer to the [original model card](https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1) for more details on the model.
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/zephyr-orpo-141b-A35b-v0.1-4bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,89 @@
+{
+    "vocab_size": 32000,
+    "max_position_embeddings": 65536,
+    "hidden_size": 6144,
+    "intermediate_size": 16384,
+    "num_hidden_layers": 56,
+    "num_attention_heads": 48,
+    "sliding_window": null,
+    "num_key_value_heads": 8,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-05,
+    "use_cache": true,
+    "rope_theta": 1000000,
+    "attention_dropout": 0.0,
+    "num_experts_per_tok": 2,
+    "num_local_experts": 8,
+    "output_router_logits": false,
+    "router_aux_loss_coef": 0.001,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": "bfloat16",
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": false,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+        "MixtralForCausalLM"
+    ],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 1,
+    "pad_token_id": null,
+    "eos_token_id": 2,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--HuggingFaceH4--zephyr-orpo-141b-A35b-v0.1/snapshots/4e5568b3b7428916cc30b38c94b282707ee5a48e",
+    "transformers_version": "4.39.3",
+    "model_type": "mixtral",
+    "router_jitter_noise": 0.0,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    }
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:968162727df205fdb5c2cda2e32fadee33144e8433d387c7d09834be65197dec
+size 5348243527

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cc72f8a6691a69ace10854be153d614259c0e36ea5f4d2174dfbac71237ddfe
+size 5351416675

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0666502ca81edf6fcea4a2a2af1d0801a921cd58d77439e7a2f16fddb98c4cce
+size 5351416739

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:404029ee2dd9c3db9fd0f7f2192c5613046cb26c0bcb7d9d8cfafd5d2ff85d54
+size 5358370680

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c670392b45b2d93970079d143299de50a5c6de2a31e2efce3ff204313af007b7
+size 5351416988

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d2e57256ede4f933b18b1c35226faec307d912ed73a04e914d0b13d11fefd7
+size 5351417004

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df95e4b17376d29a237d4de98c328b7f707d3a00d5c91c9fcfe26fae62651658
+size 5351416986

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ce85e116ed4fb152e39f3440e575d003818d15b408bd9bf3903c429f977442
+size 5351416946

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75ea87b6e7cd7e42d9a8caf127d5e3402e7866804e7481cc00a52ea37ce5d2c
+size 5358370676

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fa42310eb44896f9376bcecb82701ade47cc8236cf8e3daa764d3a40a31ca1c
+size 5351417016

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eff7e1198c4e8e9933340f10a28b34c02ccff03f39f2ebdfd19ad2ea8e337db3
+size 5351417002

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9cfb34fffba1a708947af367564d4e233c1bb6f126b6b9e7d5ad1f46adff2c4
+size 5351416958

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f070a9b9651e5ff03d216d539b5202e8010f713c20bb4b8b0fe4cb07d6b876
+size 5351416996

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac35a28280b460237ccd19b4b4483d39fe0cf1c326ff63e5e3369edbd01284f
+size 5358370654

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5a93e2acddef3e28234a40c51eab33420128463848052782796db33329b433
+size 4449777275

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}