Hugging Face's logo

sue3489
/
test0_kullm-polyglot-5.8b-v2-koalpaca-v1.1b

Text Generation
Transformers
PyTorch
Korean
gpt_neox
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
1
sue3489 commited on
Commit
8ef364c
•
1 Parent(s): 50f5568

ver.1

Browse files
Files changed (28) hide show
  1. README.md +53 -0
  2. all_results.json +8 -0
  3. checkpoint-500/config.json +27 -0
  4. checkpoint-500/generation_config.json +6 -0
  5. checkpoint-500/optimizer.pt +3 -0
  6. checkpoint-500/pytorch_model-00001-of-00003.bin +3 -0
  7. checkpoint-500/pytorch_model-00002-of-00003.bin +3 -0
  8. checkpoint-500/pytorch_model-00003-of-00003.bin +3 -0
  9. checkpoint-500/pytorch_model.bin.index.json +431 -0
  10. checkpoint-500/rng_state.pth +3 -0
  11. checkpoint-500/scheduler.pt +3 -0
  12. checkpoint-500/special_tokens_map.json +11 -0
  13. checkpoint-500/tokenizer.json +0 -0
  14. checkpoint-500/tokenizer_config.json +7 -0
  15. checkpoint-500/trainer_state.json +28 -0
  16. checkpoint-500/training_args.bin +3 -0
  17. config.json +27 -0
  18. generation_config.json +6 -0
  19. pytorch_model-00001-of-00003.bin +3 -0
  20. pytorch_model-00002-of-00003.bin +3 -0
  21. pytorch_model-00003-of-00003.bin +3 -0
  22. pytorch_model.bin.index.json +431 -0
  23. special_tokens_map.json +11 -0
  24. tokenizer.json +0 -0
  25. tokenizer_config.json +7 -0
  26. train_results.json +8 -0
  27. trainer_state.json +37 -0
  28. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: kullm-polyglot-5.8b-v2-koalpaca-v1.1b
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # kullm-polyglot-5.8b-v2-koalpaca-v1.1b
14
+
15
+ This model is a fine-tuned version of [nlpai-lab/kullm-polyglot-5.8b-v2](https://huggingface.co/nlpai-lab/kullm-polyglot-5.8b-v2) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 2e-05
35
+ - train_batch_size: 1
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - gradient_accumulation_steps: 8
39
+ - total_train_batch_size: 8
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 1.0
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.30.2
51
+ - Pytorch 2.0.1+cu117
52
+ - Datasets 2.14.4
53
+ - Tokenizers 0.13.3
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 1.8867163251699168,
4
+ "train_runtime": 2121.0416,
5
+ "train_samples": 4556,
6
+ "train_samples_per_second": 2.148,
7
+ "train_steps_per_second": 0.268
8
+ }
checkpoint-500/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nlpai-lab/kullm-polyglot-5.8b-v2",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": 0.1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16384,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "gpt_neox",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 28,
18
+ "num_steps": "global_step320000",
19
+ "rotary_emb_base": 10000,
20
+ "rotary_pct": 0.25,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.30.2",
24
+ "use_cache": true,
25
+ "use_parallel_residual": true,
26
+ "vocab_size": 30080
27
+ }
checkpoint-500/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.30.2"
6
+ }
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5d3f6ab310051fa36b275fe5510db1919ba572d3385b26ca77c9754295620b5
3
+ size 13835205
checkpoint-500/pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33035ea45a4761407863f4648c961b10985fc662551dfd6c6f23cb0240f78b01
3
+ size 9941008712
checkpoint-500/pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84c72ca9497ce6257959d12d1c17489eaa75c53e54606ee5cc079286a9296885
3
+ size 9989345398
checkpoint-500/pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c365b1b91a52f14526811d4765f011c9b5b298a9952487f64f7a752a9d3edc84
3
+ size 3727478271
checkpoint-500/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,431 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 23554920048.0
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "pytorch_model-00003-of-00003.bin",
7
+ "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00003.bin",
8
+ "gpt_neox.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
9
+ "gpt_neox.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
10
+ "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00003.bin",
11
+ "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
12
+ "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
13
+ "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
14
+ "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
15
+ "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
16
+ "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
+ "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
18
+ "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
20
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
21
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
22
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
23
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
24
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
25
+ "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00003.bin",
26
+ "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
27
+ "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
28
+ "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
29
+ "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
30
+ "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
31
+ "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
32
+ "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
33
+ "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
34
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
35
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
36
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
37
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
38
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
39
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
40
+ "gpt_neox.layers.10.attention.bias": "pytorch_model-00001-of-00003.bin",
41
+ "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
42
+ "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
43
+ "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
44
+ "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
45
+ "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
46
+ "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
+ "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
48
+ "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
50
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
51
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
52
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
53
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
54
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
55
+ "gpt_neox.layers.11.attention.bias": "pytorch_model-00001-of-00003.bin",
56
+ "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
57
+ "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
58
+ "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
59
+ "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
60
+ "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
61
+ "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
62
+ "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
63
+ "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
64
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
65
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
66
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
67
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
68
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
69
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
70
+ "gpt_neox.layers.12.attention.bias": "pytorch_model-00002-of-00003.bin",
71
+ "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
72
+ "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
73
+ "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
74
+ "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
75
+ "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
76
+ "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
77
+ "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
78
+ "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
80
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
81
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
82
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
83
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
84
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
85
+ "gpt_neox.layers.13.attention.bias": "pytorch_model-00002-of-00003.bin",
86
+ "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
87
+ "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
88
+ "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
89
+ "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
90
+ "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
91
+ "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
92
+ "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
93
+ "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
94
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
95
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
96
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
97
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
98
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
99
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
100
+ "gpt_neox.layers.14.attention.bias": "pytorch_model-00002-of-00003.bin",
101
+ "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
102
+ "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
103
+ "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
104
+ "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
105
+ "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
106
+ "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
+ "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
108
+ "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
110
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
111
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
112
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
113
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
114
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
115
+ "gpt_neox.layers.15.attention.bias": "pytorch_model-00002-of-00003.bin",
116
+ "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
117
+ "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
118
+ "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
119
+ "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
120
+ "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
121
+ "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
122
+ "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
123
+ "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
124
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
125
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
126
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
127
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
128
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
129
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
130
+ "gpt_neox.layers.16.attention.bias": "pytorch_model-00002-of-00003.bin",
131
+ "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
132
+ "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
133
+ "gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
134
+ "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
135
+ "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
136
+ "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
137
+ "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
138
+ "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
140
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
141
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
142
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
143
+ "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
144
+ "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
145
+ "gpt_neox.layers.17.attention.bias": "pytorch_model-00002-of-00003.bin",
146
+ "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
147
+ "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
148
+ "gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
149
+ "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
150
+ "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
151
+ "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
152
+ "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
153
+ "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
154
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
155
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
156
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
157
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
158
+ "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
159
+ "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
160
+ "gpt_neox.layers.18.attention.bias": "pytorch_model-00002-of-00003.bin",
161
+ "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
162
+ "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
163
+ "gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
164
+ "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
165
+ "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
166
+ "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
+ "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
168
+ "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
169
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
170
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
171
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
172
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
173
+ "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
174
+ "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
175
+ "gpt_neox.layers.19.attention.bias": "pytorch_model-00002-of-00003.bin",
176
+ "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
177
+ "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
178
+ "gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
179
+ "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
180
+ "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
181
+ "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
182
+ "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
183
+ "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
184
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
185
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
186
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
187
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
188
+ "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
189
+ "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
190
+ "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00003.bin",
191
+ "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
192
+ "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
193
+ "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
194
+ "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
195
+ "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
196
+ "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
197
+ "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
198
+ "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
199
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
200
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
201
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
202
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
203
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
204
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
205
+ "gpt_neox.layers.20.attention.bias": "pytorch_model-00002-of-00003.bin",
206
+ "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
207
+ "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
208
+ "gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
209
+ "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
210
+ "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
211
+ "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
212
+ "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
213
+ "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
214
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
215
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
216
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
217
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
218
+ "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
219
+ "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
220
+ "gpt_neox.layers.21.attention.bias": "pytorch_model-00002-of-00003.bin",
221
+ "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
222
+ "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
223
+ "gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
224
+ "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
225
+ "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
226
+ "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
227
+ "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
228
+ "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
229
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
230
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
231
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
232
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
233
+ "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
234
+ "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
235
+ "gpt_neox.layers.22.attention.bias": "pytorch_model-00002-of-00003.bin",
236
+ "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
237
+ "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
238
+ "gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
239
+ "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
240
+ "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
241
+ "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
242
+ "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
243
+ "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
244
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
245
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
246
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
247
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
248
+ "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
249
+ "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
250
+ "gpt_neox.layers.23.attention.bias": "pytorch_model-00002-of-00003.bin",
251
+ "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
252
+ "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
253
+ "gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
254
+ "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
255
+ "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
256
+ "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
257
+ "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
258
+ "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
259
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
260
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
261
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
262
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
263
+ "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
264
+ "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
265
+ "gpt_neox.layers.24.attention.bias": "pytorch_model-00002-of-00003.bin",
266
+ "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
267
+ "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
268
+ "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
269
+ "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
270
+ "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
271
+ "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
272
+ "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
273
+ "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
274
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
275
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
276
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
277
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
278
+ "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
279
+ "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
280
+ "gpt_neox.layers.25.attention.bias": "pytorch_model-00003-of-00003.bin",
281
+ "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
282
+ "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
283
+ "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
284
+ "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
285
+ "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
286
+ "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
287
+ "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
288
+ "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
289
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
290
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
291
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
292
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
293
+ "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
294
+ "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
295
+ "gpt_neox.layers.26.attention.bias": "pytorch_model-00003-of-00003.bin",
296
+ "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
297
+ "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
298
+ "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
299
+ "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
300
+ "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
301
+ "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
302
+ "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
303
+ "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
304
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
305
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
306
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
307
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
308
+ "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
309
+ "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
310
+ "gpt_neox.layers.27.attention.bias": "pytorch_model-00003-of-00003.bin",
311
+ "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
312
+ "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
313
+ "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
314
+ "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
315
+ "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
316
+ "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
317
+ "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
318
+ "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
319
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
320
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
321
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
322
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
323
+ "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
324
+ "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
325
+ "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00003.bin",
326
+ "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
327
+ "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
328
+ "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
329
+ "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
330
+ "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
331
+ "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
332
+ "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
333
+ "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
334
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
335
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
336
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
337
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
338
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
339
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
340
+ "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00003.bin",
341
+ "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
342
+ "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
343
+ "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
344
+ "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
345
+ "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
346
+ "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
347
+ "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
348
+ "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
349
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
350
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
351
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
352
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
353
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
354
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
355
+ "gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00003.bin",
356
+ "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
357
+ "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
358
+ "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
359
+ "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
360
+ "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
361
+ "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
362
+ "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
363
+ "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
364
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
365
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
366
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
367
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
368
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
369
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
370
+ "gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00003.bin",
371
+ "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
372
+ "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
373
+ "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
374
+ "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
375
+ "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
376
+ "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
377
+ "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
378
+ "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
379
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
380
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
381
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
382
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
383
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
384
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
385
+ "gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00003.bin",
386
+ "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
387
+ "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
388
+ "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
389
+ "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
390
+ "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
391
+ "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
392
+ "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
393
+ "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
394
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
395
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
396
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
397
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
398
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
399
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
400
+ "gpt_neox.layers.8.attention.bias": "pytorch_model-00001-of-00003.bin",
401
+ "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
402
+ "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
403
+ "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
404
+ "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
405
+ "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
406
+ "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
407
+ "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
408
+ "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
409
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
410
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
411
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
412
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
413
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
414
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
415
+ "gpt_neox.layers.9.attention.bias": "pytorch_model-00001-of-00003.bin",
416
+ "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
417
+ "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
418
+ "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
419
+ "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
420
+ "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
421
+ "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
422
+ "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
423
+ "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
424
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
425
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
426
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
427
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
428
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
429
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin"
430
+ }
431
+ }
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
3
+ size 14575
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b8c1ed56b6ada0dc9adda9dcd0e8427f0a04a059694948da5361355cae552fc
3
+ size 627
checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|sep|>",
5
+ "<|acc|>",
6
+ "<|tel|>",
7
+ "<|rrn|>"
8
+ ],
9
+ "eos_token": "<|endoftext|>",
10
+ "pad_token": "<|endoftext|>"
11
+ }
checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "<|endoftext|>",
4
+ "model_max_length": 1000000000000000019884624838656,
5
+ "pad_token": "<|endoftext|>",
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8779631255487269,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1.9964850615114238e-05,
13
+ "loss": 2.1598,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.88,
18
+ "learning_rate": 2.425307557117751e-06,
19
+ "loss": 1.8933,
20
+ "step": 500
21
+ }
22
+ ],
23
+ "max_steps": 569,
24
+ "num_train_epochs": 1,
25
+ "total_flos": 1.41603259809792e+17,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f24db6963114069a5c8903d3c03c7500917f1a90c382639cd9277fd8a7f061
3
+ size 3963
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nlpai-lab/kullm-polyglot-5.8b-v2",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": 0.1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16384,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "gpt_neox",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 28,
18
+ "num_steps": "global_step320000",
19
+ "rotary_emb_base": 10000,
20
+ "rotary_pct": 0.25,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.30.2",
24
+ "use_cache": true,
25
+ "use_parallel_residual": true,
26
+ "vocab_size": 30080
27
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.30.2"
6
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:414fa04a6b78634bd5034852dcbb7ab5167f7cf747292051bd5a5838167f3a13
3
+ size 9941008712
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd6e9b69639467bfbea5a581cfaa565c72baaedede33e22c54b1145da2f43f8
3
+ size 9989345398
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72fbca4b13900b30375c0fd017a01ed491777a2a0df58d5f8160fd05db81b108
3
+ size 3727478271
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,431 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 23554920048.0
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "pytorch_model-00003-of-00003.bin",
7
+ "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00003.bin",
8
+ "gpt_neox.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
9
+ "gpt_neox.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
10
+ "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00003.bin",
11
+ "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
12
+ "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
13
+ "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
14
+ "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
15
+ "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
16
+ "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
+ "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
18
+ "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
20
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
21
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
22
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
23
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
24
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
25
+ "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00003.bin",
26
+ "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
27
+ "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
28
+ "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
29
+ "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
30
+ "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
31
+ "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
32
+ "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
33
+ "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
34
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
35
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
36
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
37
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
38
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
39
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
40
+ "gpt_neox.layers.10.attention.bias": "pytorch_model-00001-of-00003.bin",
41
+ "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
42
+ "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
43
+ "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
44
+ "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
45
+ "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
46
+ "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
+ "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
48
+ "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
50
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
51
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
52
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
53
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
54
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
55
+ "gpt_neox.layers.11.attention.bias": "pytorch_model-00001-of-00003.bin",
56
+ "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
57
+ "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
58
+ "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
59
+ "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
60
+ "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
61
+ "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
62
+ "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
63
+ "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
64
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
65
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
66
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
67
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
68
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
69
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
70
+ "gpt_neox.layers.12.attention.bias": "pytorch_model-00002-of-00003.bin",
71
+ "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
72
+ "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
73
+ "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
74
+ "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
75
+ "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
76
+ "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
77
+ "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
78
+ "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
80
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
81
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
82
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
83
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
84
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
85
+ "gpt_neox.layers.13.attention.bias": "pytorch_model-00002-of-00003.bin",
86
+ "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
87
+ "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
88
+ "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
89
+ "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
90
+ "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
91
+ "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
92
+ "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
93
+ "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
94
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
95
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
96
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
97
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
98
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
99
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
100
+ "gpt_neox.layers.14.attention.bias": "pytorch_model-00002-of-00003.bin",
101
+ "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
102
+ "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
103
+ "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
104
+ "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
105
+ "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
106
+ "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
+ "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
108
+ "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
110
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
111
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
112
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
113
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
114
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
115
+ "gpt_neox.layers.15.attention.bias": "pytorch_model-00002-of-00003.bin",
116
+ "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
117
+ "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
118
+ "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
119
+ "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
120
+ "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
121
+ "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
122
+ "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
123
+ "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
124
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
125
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
126
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
127
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
128
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
129
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
130
+ "gpt_neox.layers.16.attention.bias": "pytorch_model-00002-of-00003.bin",
131
+ "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
132
+ "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
133
+ "gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
134
+ "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
135
+ "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
136
+ "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
137
+ "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
138
+ "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
140
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
141
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
142
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
143
+ "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
144
+ "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
145
+ "gpt_neox.layers.17.attention.bias": "pytorch_model-00002-of-00003.bin",
146
+ "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
147
+ "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
148
+ "gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
149
+ "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
150
+ "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
151
+ "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
152
+ "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
153
+ "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
154
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
155
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
156
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
157
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
158
+ "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
159
+ "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
160
+ "gpt_neox.layers.18.attention.bias": "pytorch_model-00002-of-00003.bin",
161
+ "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
162
+ "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
163
+ "gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
164
+ "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
165
+ "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
166
+ "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
+ "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
168
+ "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
169
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
170
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
171
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
172
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
173
+ "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
174
+ "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
175
+ "gpt_neox.layers.19.attention.bias": "pytorch_model-00002-of-00003.bin",
176
+ "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
177
+ "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
178
+ "gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
179
+ "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
180
+ "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
181
+ "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
182
+ "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
183
+ "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
184
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
185
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
186
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
187
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
188
+ "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
189
+ "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
190
+ "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00003.bin",
191
+ "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
192
+ "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
193
+ "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
194
+ "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
195
+ "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
196
+ "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
197
+ "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
198
+ "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
199
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
200
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
201
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
202
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
203
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
204
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
205
+ "gpt_neox.layers.20.attention.bias": "pytorch_model-00002-of-00003.bin",
206
+ "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
207
+ "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
208
+ "gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
209
+ "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
210
+ "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
211
+ "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
212
+ "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
213
+ "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
214
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
215
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
216
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
217
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
218
+ "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
219
+ "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
220
+ "gpt_neox.layers.21.attention.bias": "pytorch_model-00002-of-00003.bin",
221
+ "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
222
+ "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
223
+ "gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
224
+ "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
225
+ "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
226
+ "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
227
+ "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
228
+ "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
229
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
230
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
231
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
232
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
233
+ "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
234
+ "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
235
+ "gpt_neox.layers.22.attention.bias": "pytorch_model-00002-of-00003.bin",
236
+ "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
237
+ "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
238
+ "gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
239
+ "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
240
+ "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
241
+ "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
242
+ "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
243
+ "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
244
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
245
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
246
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
247
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
248
+ "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
249
+ "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
250
+ "gpt_neox.layers.23.attention.bias": "pytorch_model-00002-of-00003.bin",
251
+ "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
252
+ "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
253
+ "gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
254
+ "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
255
+ "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
256
+ "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
257
+ "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
258
+ "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
259
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
260
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
261
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
262
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
263
+ "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
264
+ "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
265
+ "gpt_neox.layers.24.attention.bias": "pytorch_model-00002-of-00003.bin",
266
+ "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
267
+ "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
268
+ "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
269
+ "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
270
+ "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
271
+ "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
272
+ "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
273
+ "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
274
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
275
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
276
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
277
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
278
+ "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
279
+ "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
280
+ "gpt_neox.layers.25.attention.bias": "pytorch_model-00003-of-00003.bin",
281
+ "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
282
+ "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
283
+ "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
284
+ "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
285
+ "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
286
+ "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
287
+ "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
288
+ "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
289
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
290
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
291
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
292
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
293
+ "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
294
+ "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
295
+ "gpt_neox.layers.26.attention.bias": "pytorch_model-00003-of-00003.bin",
296
+ "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
297
+ "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
298
+ "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
299
+ "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
300
+ "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
301
+ "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
302
+ "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
303
+ "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
304
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
305
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
306
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
307
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
308
+ "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
309
+ "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
310
+ "gpt_neox.layers.27.attention.bias": "pytorch_model-00003-of-00003.bin",
311
+ "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
312
+ "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
313
+ "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
314
+ "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
315
+ "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
316
+ "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
317
+ "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
318
+ "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
319
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
320
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
321
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
322
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
323
+ "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
324
+ "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
325
+ "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00003.bin",
326
+ "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
327
+ "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
328
+ "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
329
+ "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
330
+ "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
331
+ "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
332
+ "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
333
+ "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
334
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
335
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
336
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
337
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
338
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
339
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
340
+ "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00003.bin",
341
+ "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
342
+ "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
343
+ "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
344
+ "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
345
+ "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
346
+ "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
347
+ "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
348
+ "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
349
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
350
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
351
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
352
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
353
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
354
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
355
+ "gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00003.bin",
356
+ "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
357
+ "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
358
+ "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
359
+ "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
360
+ "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
361
+ "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
362
+ "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
363
+ "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
364
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
365
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
366
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
367
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
368
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
369
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
370
+ "gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00003.bin",
371
+ "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
372
+ "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
373
+ "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
374
+ "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
375
+ "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
376
+ "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
377
+ "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
378
+ "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
379
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
380
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
381
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
382
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
383
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
384
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
385
+ "gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00003.bin",
386
+ "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
387
+ "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
388
+ "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
389
+ "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
390
+ "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
391
+ "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
392
+ "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
393
+ "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
394
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
395
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
396
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
397
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
398
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
399
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
400
+ "gpt_neox.layers.8.attention.bias": "pytorch_model-00001-of-00003.bin",
401
+ "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
402
+ "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
403
+ "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
404
+ "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
405
+ "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
406
+ "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
407
+ "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
408
+ "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
409
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
410
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
411
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
412
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
413
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
414
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
415
+ "gpt_neox.layers.9.attention.bias": "pytorch_model-00001-of-00003.bin",
416
+ "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
417
+ "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
418
+ "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
419
+ "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
420
+ "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
421
+ "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
422
+ "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
423
+ "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
424
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
425
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
426
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
427
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
428
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
429
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin"
430
+ }
431
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|sep|>",
5
+ "<|acc|>",
6
+ "<|tel|>",
7
+ "<|rrn|>"
8
+ ],
9
+ "eos_token": "<|endoftext|>",
10
+ "pad_token": "<|endoftext|>"
11
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "<|endoftext|>",
4
+ "model_max_length": 1000000000000000019884624838656,
5
+ "pad_token": "<|endoftext|>",
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 1.8867163251699168,
4
+ "train_runtime": 2121.0416,
5
+ "train_samples": 4556,
6
+ "train_samples_per_second": 2.148,
7
+ "train_steps_per_second": 0.268
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9991220368744512,
5
+ "global_step": 569,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1.9964850615114238e-05,
13
+ "loss": 2.1598,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.88,
18
+ "learning_rate": 2.425307557117751e-06,
19
+ "loss": 1.8933,
20
+ "step": 500
21
+ },
22
+ {
23
+ "epoch": 1.0,
24
+ "step": 569,
25
+ "total_flos": 1.611445096635433e+17,
26
+ "train_loss": 1.8867163251699168,
27
+ "train_runtime": 2121.0416,
28
+ "train_samples_per_second": 2.148,
29
+ "train_steps_per_second": 0.268
30
+ }
31
+ ],
32
+ "max_steps": 569,
33
+ "num_train_epochs": 1,
34
+ "total_flos": 1.611445096635433e+17,
35
+ "trial_name": null,
36
+ "trial_params": null
37
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f24db6963114069a5c8903d3c03c7500917f1a90c382639cd9277fd8a7f061
3
+ size 3963