Hugging Face's logo

pints-ai
/
Llama-3.1-8B-Instruct-RAG_Baseline_tuned-1

Model card Files Community
zpdeaccount commited on
Commit
251f549
·
verified ·
1 Parent(s): 582bd14

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. checkpoint-10/config.json +38 -0
  2. checkpoint-10/pytorch_model.bin +3 -0
  3. checkpoint-10/random_states_0.pkl +3 -0
  4. checkpoint-10/scheduler.bin +3 -0
  5. checkpoint-2/config.json +38 -0
  6. checkpoint-2/pytorch_model.bin +3 -0
  7. checkpoint-2/random_states_0.pkl +3 -0
  8. checkpoint-2/scheduler.bin +3 -0
  9. checkpoint-4/config.json +38 -0
  10. checkpoint-4/pytorch_model.bin +3 -0
  11. checkpoint-4/random_states_0.pkl +3 -0
  12. checkpoint-4/scheduler.bin +3 -0
  13. checkpoint-6/config.json +38 -0
  14. checkpoint-6/pytorch_model.bin +3 -0
  15. checkpoint-6/random_states_0.pkl +3 -0
  16. checkpoint-6/scheduler.bin +3 -0
  17. checkpoint-8/config.json +38 -0
  18. checkpoint-8/pytorch_model.bin +3 -0
  19. checkpoint-8/random_states_0.pkl +3 -0
  20. checkpoint-8/scheduler.bin +3 -0
checkpoint-10/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 14336,
17
+ "max_position_embeddings": 131072,
18
+ "mlp_bias": false,
19
+ "model_type": "llama",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
+ "factor": 8.0,
27
+ "low_freq_factor": 1.0,
28
+ "high_freq_factor": 4.0,
29
+ "original_max_position_embeddings": 8192,
30
+ "rope_type": "llama3"
31
+ },
32
+ "rope_theta": 500000.0,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.42.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }
checkpoint-10/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:102e3a32a12d336896a89dcb915d331b13d15a036d3c2ab4c903ad3772b82190
3
+ size 32121081646
checkpoint-10/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9e523cfa355bd1f04d85ce205868c52311d8c1fd027ea0eb5b2b68b72883d9a
3
+ size 14344
checkpoint-10/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e561437b2360cb3e26c839472215503265b3009cba62bd8d903af0c3632e99d1
3
+ size 1064
checkpoint-2/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 14336,
17
+ "max_position_embeddings": 131072,
18
+ "mlp_bias": false,
19
+ "model_type": "llama",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
+ "factor": 8.0,
27
+ "low_freq_factor": 1.0,
28
+ "high_freq_factor": 4.0,
29
+ "original_max_position_embeddings": 8192,
30
+ "rope_type": "llama3"
31
+ },
32
+ "rope_theta": 500000.0,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.42.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }
checkpoint-2/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:664b3de37d0c15810a05510b77982241a9589d51f43d4b531012e0de34ce4b35
3
+ size 32121081646
checkpoint-2/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7376e979b6844de78225fbbb8434459267dbdb24ef40d5277b716a5eb2d27634
3
+ size 14344
checkpoint-2/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50090b464b359e40718bf6de515bd89382d366a7f008bbc693c172cfed3018dc
3
+ size 1064
checkpoint-4/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 14336,
17
+ "max_position_embeddings": 131072,
18
+ "mlp_bias": false,
19
+ "model_type": "llama",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
+ "factor": 8.0,
27
+ "low_freq_factor": 1.0,
28
+ "high_freq_factor": 4.0,
29
+ "original_max_position_embeddings": 8192,
30
+ "rope_type": "llama3"
31
+ },
32
+ "rope_theta": 500000.0,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.42.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }
checkpoint-4/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aac712e6a012ff18d7f2414b2a8644881f3190a6fe709115f37dd1e1c25dcc56
3
+ size 32121081646
checkpoint-4/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa76d5f23f2b36cc3d6ac3e3a827b46518da67a3d0472bcb7092ca5aa728eed1
3
+ size 14344
checkpoint-4/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f80638cf470c5c150b7ed2c0ef07513df7d1e1efa0fe811a93dce93acfa3304
3
+ size 1064
checkpoint-6/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 14336,
17
+ "max_position_embeddings": 131072,
18
+ "mlp_bias": false,
19
+ "model_type": "llama",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
+ "factor": 8.0,
27
+ "low_freq_factor": 1.0,
28
+ "high_freq_factor": 4.0,
29
+ "original_max_position_embeddings": 8192,
30
+ "rope_type": "llama3"
31
+ },
32
+ "rope_theta": 500000.0,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.42.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }
checkpoint-6/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8109e746a043abbc2effa9ebe7a4f572861bd4698194aa3c098ebfe88327637
3
+ size 32121081646
checkpoint-6/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de81d15876d7bf8189e0834b04c8d7cddf0d27064c0e85d1fbdd52afcd7d2873
3
+ size 14344
checkpoint-6/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb6affc75773a4a9ab9cba07e94c22e5d67b9defe71007f6e3a5b4db7d3386b
3
+ size 1064
checkpoint-8/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 14336,
17
+ "max_position_embeddings": 131072,
18
+ "mlp_bias": false,
19
+ "model_type": "llama",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
+ "factor": 8.0,
27
+ "low_freq_factor": 1.0,
28
+ "high_freq_factor": 4.0,
29
+ "original_max_position_embeddings": 8192,
30
+ "rope_type": "llama3"
31
+ },
32
+ "rope_theta": 500000.0,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.42.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }
checkpoint-8/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e9d2bf454d7cacc5cfbee0778d950a73c85668ad154fea3c70a68fedc59865
3
+ size 32121081646
checkpoint-8/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b249acf3694d73ddd41e443b055e3fede82349e1e47b52acc1b96a6434fd977
3
+ size 14344
checkpoint-8/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a77624b8e5cc7f1b3becb8a420a7a970d45b50ad2103ab9500ef1c68c424809
3
+ size 1064