AlekseyKorshuk commited on
Commit
0ab3bd1
1 Parent(s): 2b31feb

End of training

Browse files
README.md ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bigcode-openrail-m
3
+ base_model: WizardLM/WizardCoder-3B-V1.0
4
+ tags:
5
+ - axolotl
6
+ - dpo
7
+ - trl
8
+ - dpo
9
+ - generated_from_trainer
10
+ model-index:
11
+ - name: WizardCoder-3B-V1.0-dpo-beta-0.01
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
19
+ <details><summary>See axolotl config</summary>
20
+
21
+ axolotl version: `0.4.0`
22
+ ```yaml
23
+ base_model: WizardLM/WizardCoder-3B-V1.0
24
+ model_type: AutoModelForCausalLM
25
+ tokenizer_type: AutoTokenizer
26
+ trust_remote_code: true
27
+
28
+ hub_model_id: AlekseyKorshuk/WizardCoder-3B-V1.0-dpo-beta-0.01
29
+ hub_strategy: every_save
30
+
31
+ load_in_8bit: false
32
+ load_in_4bit: false
33
+ strict: false
34
+
35
+ rl: dpo
36
+ datasets:
37
+ - path: AlekseyKorshuk/evol-codealpaca-v1-dpo
38
+ split: train
39
+ type: wizardcoder.intel
40
+ dataset_prepared_path: last_run_prepared
41
+
42
+ #val_set_size: 0.001
43
+ output_dir: ./output
44
+
45
+ sequence_len: 2048
46
+ #sample_packing: false # currently unsupported
47
+ pad_to_sequence_len:
48
+
49
+ lora_r:
50
+ lora_alpha:
51
+ lora_dropout:
52
+ lora_target_modules:
53
+ lora_target_linear:
54
+ lora_fan_in_fan_out:
55
+
56
+ wandb_project: ui-thesis
57
+ wandb_entity:
58
+ wandb_watch:
59
+ wandb_name: WizardCoder-3B-V1.0-dpo-beta-0.01
60
+ wandb_log_model:
61
+
62
+ gradient_accumulation_steps: 4
63
+ micro_batch_size: 8
64
+ num_epochs: 1
65
+ optimizer: paged_adamw_8bit
66
+ adam_beta1: 0.9
67
+ adam_beta2: 0.95
68
+ max_grad_norm: 1.0
69
+ adam_epsilon: 0.00001
70
+ lr_scheduler: cosine
71
+ cosine_min_lr_ratio: 0.1
72
+ learning_rate: 8.0e-7
73
+ warmup_steps: 32
74
+ #warmup_ratio: 0.1
75
+ weight_decay: 0.01
76
+ dpo_beta: 0.01
77
+
78
+ train_on_inputs: false
79
+ group_by_length: false
80
+ bf16: true
81
+ fp16: false
82
+ tf32: true
83
+ #float16: false
84
+ #bfloat16: false
85
+
86
+ gradient_checkpointing: true
87
+ early_stopping_patience:
88
+ resume_from_checkpoint:
89
+ local_rank:
90
+ logging_steps: 1
91
+ xformers_attention:
92
+ flash_attention: false
93
+
94
+
95
+ #evals_per_epoch: 5
96
+ #eval_table_size: 8 # Approximate number of predictions sent to wandb depending on batch size. Enabled above 0. Default is 0
97
+ #eval_table_max_new_tokens: 768 # Total number of tokens generated for predictions sent to wandb. Default is 128
98
+
99
+ #chat_template: chatml
100
+ #saves_per_epoch: 1
101
+ save_steps: 500
102
+ save_total_limit: 1
103
+ seed: 42
104
+ debug:
105
+ deepspeed:
106
+
107
+
108
+ fsdp:
109
+ fsdp_config:
110
+ resize_token_embeddings_to_32x: true
111
+
112
+ ```
113
+
114
+ </details><br>
115
+
116
+ # WizardCoder-3B-V1.0-dpo-beta-0.01
117
+
118
+ This model is a fine-tuned version of [WizardLM/WizardCoder-3B-V1.0](https://huggingface.co/WizardLM/WizardCoder-3B-V1.0) on the None dataset.
119
+
120
+ ## Model description
121
+
122
+ More information needed
123
+
124
+ ## Intended uses & limitations
125
+
126
+ More information needed
127
+
128
+ ## Training and evaluation data
129
+
130
+ More information needed
131
+
132
+ ## Training procedure
133
+
134
+ ### Training hyperparameters
135
+
136
+ The following hyperparameters were used during training:
137
+ - learning_rate: 8e-07
138
+ - train_batch_size: 8
139
+ - eval_batch_size: 8
140
+ - seed: 42
141
+ - distributed_type: multi-GPU
142
+ - num_devices: 4
143
+ - gradient_accumulation_steps: 4
144
+ - total_train_batch_size: 128
145
+ - total_eval_batch_size: 32
146
+ - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
147
+ - lr_scheduler_type: cosine
148
+ - lr_scheduler_warmup_steps: 32
149
+ - training_steps: 312
150
+
151
+ ### Training results
152
+
153
+
154
+
155
+ ### Framework versions
156
+
157
+ - Transformers 4.38.0.dev0
158
+ - Pytorch 2.1.2+cu118
159
+ - Datasets 2.16.1
160
+ - Tokenizers 0.15.0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 49152
3
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "WizardLM/WizardCoder-3B-V1.0",
3
+ "activation_function": "gelu_pytorch_tanh",
4
+ "architectures": [
5
+ "GPTBigCodeForCausalLM"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 0,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 0,
12
+ "inference_runner": 0,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_batch_size": null,
16
+ "max_sequence_length": null,
17
+ "model_type": "gpt_bigcode",
18
+ "multi_query": true,
19
+ "n_embd": 2816,
20
+ "n_head": 22,
21
+ "n_inner": 11264,
22
+ "n_layer": 36,
23
+ "n_positions": 8192,
24
+ "pad_key_length": true,
25
+ "pre_allocate_kv_cache": false,
26
+ "resid_pdrop": 0.1,
27
+ "scale_attention_softmax_in_fp32": true,
28
+ "scale_attn_weights": true,
29
+ "summary_activation": null,
30
+ "summary_first_dropout": 0.1,
31
+ "summary_proj_to_labels": true,
32
+ "summary_type": "cls_index",
33
+ "summary_use_proj": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.38.0.dev0",
36
+ "use_cache": false,
37
+ "validate_runner_input": true,
38
+ "vocab_size": 49184
39
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "do_sample": true,
5
+ "eos_token_id": 0,
6
+ "transformers_version": "4.38.0.dev0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a81d7edf655444d727ffc9bf798868d3965862f30ca65270bf9a9ed96be9d7f
3
+ size 4956114120
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cb88c2de60aa37837ac9a9d8b5d3c7b90dd5819461eff8637134b50da752467
3
+ size 1407738896
model.safetensors.index.json ADDED
@@ -0,0 +1,443 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6363806720
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.attn.c_attn.bias": "model-00001-of-00002.safetensors",
7
+ "transformer.h.0.attn.c_attn.weight": "model-00001-of-00002.safetensors",
8
+ "transformer.h.0.attn.c_proj.bias": "model-00001-of-00002.safetensors",
9
+ "transformer.h.0.attn.c_proj.weight": "model-00001-of-00002.safetensors",
10
+ "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
11
+ "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
12
+ "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
13
+ "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
14
+ "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
15
+ "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
16
+ "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
17
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
18
+ "transformer.h.1.attn.c_attn.bias": "model-00001-of-00002.safetensors",
19
+ "transformer.h.1.attn.c_attn.weight": "model-00001-of-00002.safetensors",
20
+ "transformer.h.1.attn.c_proj.bias": "model-00001-of-00002.safetensors",
21
+ "transformer.h.1.attn.c_proj.weight": "model-00001-of-00002.safetensors",
22
+ "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
23
+ "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
24
+ "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
25
+ "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
26
+ "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
27
+ "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
28
+ "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
29
+ "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
30
+ "transformer.h.10.attn.c_attn.bias": "model-00001-of-00002.safetensors",
31
+ "transformer.h.10.attn.c_attn.weight": "model-00001-of-00002.safetensors",
32
+ "transformer.h.10.attn.c_proj.bias": "model-00001-of-00002.safetensors",
33
+ "transformer.h.10.attn.c_proj.weight": "model-00001-of-00002.safetensors",
34
+ "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
35
+ "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
36
+ "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
37
+ "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
38
+ "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
39
+ "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
40
+ "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
41
+ "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
42
+ "transformer.h.11.attn.c_attn.bias": "model-00001-of-00002.safetensors",
43
+ "transformer.h.11.attn.c_attn.weight": "model-00001-of-00002.safetensors",
44
+ "transformer.h.11.attn.c_proj.bias": "model-00001-of-00002.safetensors",
45
+ "transformer.h.11.attn.c_proj.weight": "model-00001-of-00002.safetensors",
46
+ "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
47
+ "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
48
+ "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
49
+ "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
50
+ "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
51
+ "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
52
+ "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
53
+ "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
54
+ "transformer.h.12.attn.c_attn.bias": "model-00001-of-00002.safetensors",
55
+ "transformer.h.12.attn.c_attn.weight": "model-00001-of-00002.safetensors",
56
+ "transformer.h.12.attn.c_proj.bias": "model-00001-of-00002.safetensors",
57
+ "transformer.h.12.attn.c_proj.weight": "model-00001-of-00002.safetensors",
58
+ "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
59
+ "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
60
+ "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
61
+ "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
62
+ "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
63
+ "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
64
+ "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
65
+ "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
66
+ "transformer.h.13.attn.c_attn.bias": "model-00001-of-00002.safetensors",
67
+ "transformer.h.13.attn.c_attn.weight": "model-00001-of-00002.safetensors",
68
+ "transformer.h.13.attn.c_proj.bias": "model-00001-of-00002.safetensors",
69
+ "transformer.h.13.attn.c_proj.weight": "model-00001-of-00002.safetensors",
70
+ "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
71
+ "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
72
+ "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
73
+ "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
74
+ "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
75
+ "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
76
+ "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
77
+ "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
78
+ "transformer.h.14.attn.c_attn.bias": "model-00001-of-00002.safetensors",
79
+ "transformer.h.14.attn.c_attn.weight": "model-00001-of-00002.safetensors",
80
+ "transformer.h.14.attn.c_proj.bias": "model-00001-of-00002.safetensors",
81
+ "transformer.h.14.attn.c_proj.weight": "model-00001-of-00002.safetensors",
82
+ "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
83
+ "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
84
+ "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
85
+ "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
86
+ "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
87
+ "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
88
+ "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
89
+ "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
90
+ "transformer.h.15.attn.c_attn.bias": "model-00001-of-00002.safetensors",
91
+ "transformer.h.15.attn.c_attn.weight": "model-00001-of-00002.safetensors",
92
+ "transformer.h.15.attn.c_proj.bias": "model-00001-of-00002.safetensors",
93
+ "transformer.h.15.attn.c_proj.weight": "model-00001-of-00002.safetensors",
94
+ "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
95
+ "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
96
+ "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
97
+ "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
98
+ "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
99
+ "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
100
+ "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
101
+ "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
102
+ "transformer.h.16.attn.c_attn.bias": "model-00001-of-00002.safetensors",
103
+ "transformer.h.16.attn.c_attn.weight": "model-00001-of-00002.safetensors",
104
+ "transformer.h.16.attn.c_proj.bias": "model-00001-of-00002.safetensors",
105
+ "transformer.h.16.attn.c_proj.weight": "model-00001-of-00002.safetensors",
106
+ "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
107
+ "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
108
+ "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
109
+ "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
110
+ "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
111
+ "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
112
+ "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
113
+ "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
114
+ "transformer.h.17.attn.c_attn.bias": "model-00001-of-00002.safetensors",
115
+ "transformer.h.17.attn.c_attn.weight": "model-00001-of-00002.safetensors",
116
+ "transformer.h.17.attn.c_proj.bias": "model-00001-of-00002.safetensors",
117
+ "transformer.h.17.attn.c_proj.weight": "model-00001-of-00002.safetensors",
118
+ "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
119
+ "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
120
+ "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
121
+ "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
122
+ "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
123
+ "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
124
+ "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
125
+ "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
126
+ "transformer.h.18.attn.c_attn.bias": "model-00001-of-00002.safetensors",
127
+ "transformer.h.18.attn.c_attn.weight": "model-00001-of-00002.safetensors",
128
+ "transformer.h.18.attn.c_proj.bias": "model-00001-of-00002.safetensors",
129
+ "transformer.h.18.attn.c_proj.weight": "model-00001-of-00002.safetensors",
130
+ "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
131
+ "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
132
+ "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
133
+ "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
134
+ "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
135
+ "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
136
+ "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
137
+ "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
138
+ "transformer.h.19.attn.c_attn.bias": "model-00001-of-00002.safetensors",
139
+ "transformer.h.19.attn.c_attn.weight": "model-00001-of-00002.safetensors",
140
+ "transformer.h.19.attn.c_proj.bias": "model-00001-of-00002.safetensors",
141
+ "transformer.h.19.attn.c_proj.weight": "model-00001-of-00002.safetensors",
142
+ "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
143
+ "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
144
+ "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
145
+ "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
146
+ "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
147
+ "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
148
+ "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
149
+ "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
150
+ "transformer.h.2.attn.c_attn.bias": "model-00001-of-00002.safetensors",
151
+ "transformer.h.2.attn.c_attn.weight": "model-00001-of-00002.safetensors",
152
+ "transformer.h.2.attn.c_proj.bias": "model-00001-of-00002.safetensors",
153
+ "transformer.h.2.attn.c_proj.weight": "model-00001-of-00002.safetensors",
154
+ "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
155
+ "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
156
+ "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
157
+ "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
158
+ "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
159
+ "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
160
+ "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
161
+ "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
162
+ "transformer.h.20.attn.c_attn.bias": "model-00001-of-00002.safetensors",
163
+ "transformer.h.20.attn.c_attn.weight": "model-00001-of-00002.safetensors",
164
+ "transformer.h.20.attn.c_proj.bias": "model-00001-of-00002.safetensors",
165
+ "transformer.h.20.attn.c_proj.weight": "model-00001-of-00002.safetensors",
166
+ "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
167
+ "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
168
+ "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
169
+ "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
170
+ "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
171
+ "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
172
+ "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
173
+ "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
174
+ "transformer.h.21.attn.c_attn.bias": "model-00001-of-00002.safetensors",
175
+ "transformer.h.21.attn.c_attn.weight": "model-00001-of-00002.safetensors",
176
+ "transformer.h.21.attn.c_proj.bias": "model-00001-of-00002.safetensors",
177
+ "transformer.h.21.attn.c_proj.weight": "model-00001-of-00002.safetensors",
178
+ "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
179
+ "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
180
+ "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
181
+ "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
182
+ "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
183
+ "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
184
+ "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
185
+ "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
186
+ "transformer.h.22.attn.c_attn.bias": "model-00001-of-00002.safetensors",
187
+ "transformer.h.22.attn.c_attn.weight": "model-00001-of-00002.safetensors",
188
+ "transformer.h.22.attn.c_proj.bias": "model-00001-of-00002.safetensors",
189
+ "transformer.h.22.attn.c_proj.weight": "model-00001-of-00002.safetensors",
190
+ "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
191
+ "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
192
+ "transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
193
+ "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
194
+ "transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
195
+ "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
196
+ "transformer.h.22.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
197
+ "transformer.h.22.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
198
+ "transformer.h.23.attn.c_attn.bias": "model-00001-of-00002.safetensors",
199
+ "transformer.h.23.attn.c_attn.weight": "model-00001-of-00002.safetensors",
200
+ "transformer.h.23.attn.c_proj.bias": "model-00001-of-00002.safetensors",
201
+ "transformer.h.23.attn.c_proj.weight": "model-00001-of-00002.safetensors",
202
+ "transformer.h.23.ln_1.bias": "model-00001-of-00002.safetensors",
203
+ "transformer.h.23.ln_1.weight": "model-00001-of-00002.safetensors",
204
+ "transformer.h.23.ln_2.bias": "model-00001-of-00002.safetensors",
205
+ "transformer.h.23.ln_2.weight": "model-00001-of-00002.safetensors",
206
+ "transformer.h.23.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
207
+ "transformer.h.23.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
208
+ "transformer.h.23.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
209
+ "transformer.h.23.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
210
+ "transformer.h.24.attn.c_attn.bias": "model-00001-of-00002.safetensors",
211
+ "transformer.h.24.attn.c_attn.weight": "model-00001-of-00002.safetensors",
212
+ "transformer.h.24.attn.c_proj.bias": "model-00001-of-00002.safetensors",
213
+ "transformer.h.24.attn.c_proj.weight": "model-00001-of-00002.safetensors",
214
+ "transformer.h.24.ln_1.bias": "model-00001-of-00002.safetensors",
215
+ "transformer.h.24.ln_1.weight": "model-00001-of-00002.safetensors",
216
+ "transformer.h.24.ln_2.bias": "model-00001-of-00002.safetensors",
217
+ "transformer.h.24.ln_2.weight": "model-00001-of-00002.safetensors",
218
+ "transformer.h.24.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
219
+ "transformer.h.24.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
220
+ "transformer.h.24.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
221
+ "transformer.h.24.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
222
+ "transformer.h.25.attn.c_attn.bias": "model-00001-of-00002.safetensors",
223
+ "transformer.h.25.attn.c_attn.weight": "model-00001-of-00002.safetensors",
224
+ "transformer.h.25.attn.c_proj.bias": "model-00001-of-00002.safetensors",
225
+ "transformer.h.25.attn.c_proj.weight": "model-00001-of-00002.safetensors",
226
+ "transformer.h.25.ln_1.bias": "model-00001-of-00002.safetensors",
227
+ "transformer.h.25.ln_1.weight": "model-00001-of-00002.safetensors",
228
+ "transformer.h.25.ln_2.bias": "model-00001-of-00002.safetensors",
229
+ "transformer.h.25.ln_2.weight": "model-00001-of-00002.safetensors",
230
+ "transformer.h.25.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
231
+ "transformer.h.25.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
232
+ "transformer.h.25.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
233
+ "transformer.h.25.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
234
+ "transformer.h.26.attn.c_attn.bias": "model-00001-of-00002.safetensors",
235
+ "transformer.h.26.attn.c_attn.weight": "model-00001-of-00002.safetensors",
236
+ "transformer.h.26.attn.c_proj.bias": "model-00001-of-00002.safetensors",
237
+ "transformer.h.26.attn.c_proj.weight": "model-00001-of-00002.safetensors",
238
+ "transformer.h.26.ln_1.bias": "model-00001-of-00002.safetensors",
239
+ "transformer.h.26.ln_1.weight": "model-00001-of-00002.safetensors",
240
+ "transformer.h.26.ln_2.bias": "model-00001-of-00002.safetensors",
241
+ "transformer.h.26.ln_2.weight": "model-00001-of-00002.safetensors",
242
+ "transformer.h.26.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
243
+ "transformer.h.26.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
244
+ "transformer.h.26.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
245
+ "transformer.h.26.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
246
+ "transformer.h.27.attn.c_attn.bias": "model-00001-of-00002.safetensors",
247
+ "transformer.h.27.attn.c_attn.weight": "model-00001-of-00002.safetensors",
248
+ "transformer.h.27.attn.c_proj.bias": "model-00001-of-00002.safetensors",
249
+ "transformer.h.27.attn.c_proj.weight": "model-00001-of-00002.safetensors",
250
+ "transformer.h.27.ln_1.bias": "model-00001-of-00002.safetensors",
251
+ "transformer.h.27.ln_1.weight": "model-00001-of-00002.safetensors",
252
+ "transformer.h.27.ln_2.bias": "model-00001-of-00002.safetensors",
253
+ "transformer.h.27.ln_2.weight": "model-00001-of-00002.safetensors",
254
+ "transformer.h.27.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
255
+ "transformer.h.27.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
256
+ "transformer.h.27.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
257
+ "transformer.h.27.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
258
+ "transformer.h.28.attn.c_attn.bias": "model-00002-of-00002.safetensors",
259
+ "transformer.h.28.attn.c_attn.weight": "model-00002-of-00002.safetensors",
260
+ "transformer.h.28.attn.c_proj.bias": "model-00002-of-00002.safetensors",
261
+ "transformer.h.28.attn.c_proj.weight": "model-00002-of-00002.safetensors",
262
+ "transformer.h.28.ln_1.bias": "model-00002-of-00002.safetensors",
263
+ "transformer.h.28.ln_1.weight": "model-00002-of-00002.safetensors",
264
+ "transformer.h.28.ln_2.bias": "model-00002-of-00002.safetensors",
265
+ "transformer.h.28.ln_2.weight": "model-00002-of-00002.safetensors",
266
+ "transformer.h.28.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
267
+ "transformer.h.28.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
268
+ "transformer.h.28.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
269
+ "transformer.h.28.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
270
+ "transformer.h.29.attn.c_attn.bias": "model-00002-of-00002.safetensors",
271
+ "transformer.h.29.attn.c_attn.weight": "model-00002-of-00002.safetensors",
272
+ "transformer.h.29.attn.c_proj.bias": "model-00002-of-00002.safetensors",
273
+ "transformer.h.29.attn.c_proj.weight": "model-00002-of-00002.safetensors",
274
+ "transformer.h.29.ln_1.bias": "model-00002-of-00002.safetensors",
275
+ "transformer.h.29.ln_1.weight": "model-00002-of-00002.safetensors",
276
+ "transformer.h.29.ln_2.bias": "model-00002-of-00002.safetensors",
277
+ "transformer.h.29.ln_2.weight": "model-00002-of-00002.safetensors",
278
+ "transformer.h.29.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
279
+ "transformer.h.29.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
280
+ "transformer.h.29.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
281
+ "transformer.h.29.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
282
+ "transformer.h.3.attn.c_attn.bias": "model-00001-of-00002.safetensors",
283
+ "transformer.h.3.attn.c_attn.weight": "model-00001-of-00002.safetensors",
284
+ "transformer.h.3.attn.c_proj.bias": "model-00001-of-00002.safetensors",
285
+ "transformer.h.3.attn.c_proj.weight": "model-00001-of-00002.safetensors",
286
+ "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
287
+ "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
288
+ "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
289
+ "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
290
+ "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
291
+ "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
292
+ "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
293
+ "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
294
+ "transformer.h.30.attn.c_attn.bias": "model-00002-of-00002.safetensors",
295
+ "transformer.h.30.attn.c_attn.weight": "model-00002-of-00002.safetensors",
296
+ "transformer.h.30.attn.c_proj.bias": "model-00002-of-00002.safetensors",
297
+ "transformer.h.30.attn.c_proj.weight": "model-00002-of-00002.safetensors",
298
+ "transformer.h.30.ln_1.bias": "model-00002-of-00002.safetensors",
299
+ "transformer.h.30.ln_1.weight": "model-00002-of-00002.safetensors",
300
+ "transformer.h.30.ln_2.bias": "model-00002-of-00002.safetensors",
301
+ "transformer.h.30.ln_2.weight": "model-00002-of-00002.safetensors",
302
+ "transformer.h.30.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
303
+ "transformer.h.30.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
304
+ "transformer.h.30.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
305
+ "transformer.h.30.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
306
+ "transformer.h.31.attn.c_attn.bias": "model-00002-of-00002.safetensors",
307
+ "transformer.h.31.attn.c_attn.weight": "model-00002-of-00002.safetensors",
308
+ "transformer.h.31.attn.c_proj.bias": "model-00002-of-00002.safetensors",
309
+ "transformer.h.31.attn.c_proj.weight": "model-00002-of-00002.safetensors",
310
+ "transformer.h.31.ln_1.bias": "model-00002-of-00002.safetensors",
311
+ "transformer.h.31.ln_1.weight": "model-00002-of-00002.safetensors",
312
+ "transformer.h.31.ln_2.bias": "model-00002-of-00002.safetensors",
313
+ "transformer.h.31.ln_2.weight": "model-00002-of-00002.safetensors",
314
+ "transformer.h.31.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
315
+ "transformer.h.31.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
316
+ "transformer.h.31.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
317
+ "transformer.h.31.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
318
+ "transformer.h.32.attn.c_attn.bias": "model-00002-of-00002.safetensors",
319
+ "transformer.h.32.attn.c_attn.weight": "model-00002-of-00002.safetensors",
320
+ "transformer.h.32.attn.c_proj.bias": "model-00002-of-00002.safetensors",
321
+ "transformer.h.32.attn.c_proj.weight": "model-00002-of-00002.safetensors",
322
+ "transformer.h.32.ln_1.bias": "model-00002-of-00002.safetensors",
323
+ "transformer.h.32.ln_1.weight": "model-00002-of-00002.safetensors",
324
+ "transformer.h.32.ln_2.bias": "model-00002-of-00002.safetensors",
325
+ "transformer.h.32.ln_2.weight": "model-00002-of-00002.safetensors",
326
+ "transformer.h.32.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
327
+ "transformer.h.32.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
328
+ "transformer.h.32.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
329
+ "transformer.h.32.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
330
+ "transformer.h.33.attn.c_attn.bias": "model-00002-of-00002.safetensors",
331
+ "transformer.h.33.attn.c_attn.weight": "model-00002-of-00002.safetensors",
332
+ "transformer.h.33.attn.c_proj.bias": "model-00002-of-00002.safetensors",
333
+ "transformer.h.33.attn.c_proj.weight": "model-00002-of-00002.safetensors",
334
+ "transformer.h.33.ln_1.bias": "model-00002-of-00002.safetensors",
335
+ "transformer.h.33.ln_1.weight": "model-00002-of-00002.safetensors",
336
+ "transformer.h.33.ln_2.bias": "model-00002-of-00002.safetensors",
337
+ "transformer.h.33.ln_2.weight": "model-00002-of-00002.safetensors",
338
+ "transformer.h.33.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
339
+ "transformer.h.33.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
340
+ "transformer.h.33.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
341
+ "transformer.h.33.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
342
+ "transformer.h.34.attn.c_attn.bias": "model-00002-of-00002.safetensors",
343
+ "transformer.h.34.attn.c_attn.weight": "model-00002-of-00002.safetensors",
344
+ "transformer.h.34.attn.c_proj.bias": "model-00002-of-00002.safetensors",
345
+ "transformer.h.34.attn.c_proj.weight": "model-00002-of-00002.safetensors",
346
+ "transformer.h.34.ln_1.bias": "model-00002-of-00002.safetensors",
347
+ "transformer.h.34.ln_1.weight": "model-00002-of-00002.safetensors",
348
+ "transformer.h.34.ln_2.bias": "model-00002-of-00002.safetensors",
349
+ "transformer.h.34.ln_2.weight": "model-00002-of-00002.safetensors",
350
+ "transformer.h.34.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
351
+ "transformer.h.34.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
352
+ "transformer.h.34.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
353
+ "transformer.h.34.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
354
+ "transformer.h.35.attn.c_attn.bias": "model-00002-of-00002.safetensors",
355
+ "transformer.h.35.attn.c_attn.weight": "model-00002-of-00002.safetensors",
356
+ "transformer.h.35.attn.c_proj.bias": "model-00002-of-00002.safetensors",
357
+ "transformer.h.35.attn.c_proj.weight": "model-00002-of-00002.safetensors",
358
+ "transformer.h.35.ln_1.bias": "model-00002-of-00002.safetensors",
359
+ "transformer.h.35.ln_1.weight": "model-00002-of-00002.safetensors",
360
+ "transformer.h.35.ln_2.bias": "model-00002-of-00002.safetensors",
361
+ "transformer.h.35.ln_2.weight": "model-00002-of-00002.safetensors",
362
+ "transformer.h.35.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
363
+ "transformer.h.35.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
364
+ "transformer.h.35.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
365
+ "transformer.h.35.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
366
+ "transformer.h.4.attn.c_attn.bias": "model-00001-of-00002.safetensors",
367
+ "transformer.h.4.attn.c_attn.weight": "model-00001-of-00002.safetensors",
368
+ "transformer.h.4.attn.c_proj.bias": "model-00001-of-00002.safetensors",
369
+ "transformer.h.4.attn.c_proj.weight": "model-00001-of-00002.safetensors",
370
+ "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
371
+ "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
372
+ "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
373
+ "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
374
+ "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
375
+ "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
376
+ "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
377
+ "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
378
+ "transformer.h.5.attn.c_attn.bias": "model-00001-of-00002.safetensors",
379
+ "transformer.h.5.attn.c_attn.weight": "model-00001-of-00002.safetensors",
380
+ "transformer.h.5.attn.c_proj.bias": "model-00001-of-00002.safetensors",
381
+ "transformer.h.5.attn.c_proj.weight": "model-00001-of-00002.safetensors",
382
+ "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
383
+ "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
384
+ "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
385
+ "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
386
+ "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
387
+ "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
388
+ "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
389
+ "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
390
+ "transformer.h.6.attn.c_attn.bias": "model-00001-of-00002.safetensors",
391
+ "transformer.h.6.attn.c_attn.weight": "model-00001-of-00002.safetensors",
392
+ "transformer.h.6.attn.c_proj.bias": "model-00001-of-00002.safetensors",
393
+ "transformer.h.6.attn.c_proj.weight": "model-00001-of-00002.safetensors",
394
+ "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
395
+ "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
396
+ "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
397
+ "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
398
+ "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
399
+ "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
400
+ "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
401
+ "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
402
+ "transformer.h.7.attn.c_attn.bias": "model-00001-of-00002.safetensors",
403
+ "transformer.h.7.attn.c_attn.weight": "model-00001-of-00002.safetensors",
404
+ "transformer.h.7.attn.c_proj.bias": "model-00001-of-00002.safetensors",
405
+ "transformer.h.7.attn.c_proj.weight": "model-00001-of-00002.safetensors",
406
+ "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
407
+ "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
408
+ "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
409
+ "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
410
+ "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
411
+ "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
412
+ "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
413
+ "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
414
+ "transformer.h.8.attn.c_attn.bias": "model-00001-of-00002.safetensors",
415
+ "transformer.h.8.attn.c_attn.weight": "model-00001-of-00002.safetensors",
416
+ "transformer.h.8.attn.c_proj.bias": "model-00001-of-00002.safetensors",
417
+ "transformer.h.8.attn.c_proj.weight": "model-00001-of-00002.safetensors",
418
+ "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
419
+ "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
420
+ "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
421
+ "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
422
+ "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
423
+ "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
424
+ "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
425
+ "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
426
+ "transformer.h.9.attn.c_attn.bias": "model-00001-of-00002.safetensors",
427
+ "transformer.h.9.attn.c_attn.weight": "model-00001-of-00002.safetensors",
428
+ "transformer.h.9.attn.c_proj.bias": "model-00001-of-00002.safetensors",
429
+ "transformer.h.9.attn.c_proj.weight": "model-00001-of-00002.safetensors",
430
+ "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
431
+ "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
432
+ "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
433
+ "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
434
+ "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
435
+ "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
436
+ "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
437
+ "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
438
+ "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
439
+ "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
440
+ "transformer.wpe.weight": "model-00001-of-00002.safetensors",
441
+ "transformer.wte.weight": "model-00001-of-00002.safetensors"
442
+ }
443
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f3035eaadcb7804b2ae8529982db7c7010d9c9e485500b4046721269f4abca
3
+ size 4956193872
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4798759739bbd709718d257afe4101141db33efe1e4bfac7895bc1bebf565549
3
+ size 1407763224
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,444 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6363806720
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00002.bin",
7
+ "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
8
+ "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
9
+ "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
10
+ "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
12
+ "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
13
+ "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00002.bin",
14
+ "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00002.bin",
15
+ "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
16
+ "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
17
+ "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
18
+ "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
20
+ "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
21
+ "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
22
+ "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
24
+ "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
25
+ "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00002.bin",
26
+ "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00002.bin",
27
+ "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
28
+ "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
29
+ "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
30
+ "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
32
+ "transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
33
+ "transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
34
+ "transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
36
+ "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
37
+ "transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00002.bin",
38
+ "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00002.bin",
39
+ "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
40
+ "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
41
+ "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
42
+ "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
44
+ "transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
45
+ "transformer.h.11.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
46
+ "transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
48
+ "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
49
+ "transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00002.bin",
50
+ "transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00002.bin",
51
+ "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
52
+ "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
53
+ "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
54
+ "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
56
+ "transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
57
+ "transformer.h.12.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
58
+ "transformer.h.12.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
60
+ "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
61
+ "transformer.h.12.ln_2.bias": "pytorch_model-00001-of-00002.bin",
62
+ "transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00002.bin",
63
+ "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
64
+ "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
65
+ "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
66
+ "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "transformer.h.13.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
68
+ "transformer.h.13.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
69
+ "transformer.h.13.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
70
+ "transformer.h.13.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
72
+ "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
73
+ "transformer.h.13.ln_2.bias": "pytorch_model-00001-of-00002.bin",
74
+ "transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00002.bin",
75
+ "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
76
+ "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
77
+ "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
78
+ "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
79
+ "transformer.h.14.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
80
+ "transformer.h.14.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
81
+ "transformer.h.14.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
82
+ "transformer.h.14.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
84
+ "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
85
+ "transformer.h.14.ln_2.bias": "pytorch_model-00001-of-00002.bin",
86
+ "transformer.h.14.ln_2.weight": "pytorch_model-00001-of-00002.bin",
87
+ "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
88
+ "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
89
+ "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
90
+ "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "transformer.h.15.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
92
+ "transformer.h.15.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
93
+ "transformer.h.15.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
94
+ "transformer.h.15.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
96
+ "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
97
+ "transformer.h.15.ln_2.bias": "pytorch_model-00001-of-00002.bin",
98
+ "transformer.h.15.ln_2.weight": "pytorch_model-00001-of-00002.bin",
99
+ "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
100
+ "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
101
+ "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
102
+ "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
103
+ "transformer.h.16.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
104
+ "transformer.h.16.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
105
+ "transformer.h.16.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
106
+ "transformer.h.16.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
107
+ "transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
108
+ "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
109
+ "transformer.h.16.ln_2.bias": "pytorch_model-00001-of-00002.bin",
110
+ "transformer.h.16.ln_2.weight": "pytorch_model-00001-of-00002.bin",
111
+ "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
112
+ "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
113
+ "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
114
+ "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "transformer.h.17.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
116
+ "transformer.h.17.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
117
+ "transformer.h.17.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
118
+ "transformer.h.17.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
120
+ "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
121
+ "transformer.h.17.ln_2.bias": "pytorch_model-00001-of-00002.bin",
122
+ "transformer.h.17.ln_2.weight": "pytorch_model-00001-of-00002.bin",
123
+ "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
124
+ "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
125
+ "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
126
+ "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
127
+ "transformer.h.18.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
128
+ "transformer.h.18.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
129
+ "transformer.h.18.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
130
+ "transformer.h.18.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
132
+ "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
133
+ "transformer.h.18.ln_2.bias": "pytorch_model-00001-of-00002.bin",
134
+ "transformer.h.18.ln_2.weight": "pytorch_model-00001-of-00002.bin",
135
+ "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
136
+ "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
137
+ "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
138
+ "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
139
+ "transformer.h.19.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
140
+ "transformer.h.19.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
141
+ "transformer.h.19.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
142
+ "transformer.h.19.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
143
+ "transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
144
+ "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
145
+ "transformer.h.19.ln_2.bias": "pytorch_model-00001-of-00002.bin",
146
+ "transformer.h.19.ln_2.weight": "pytorch_model-00001-of-00002.bin",
147
+ "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
148
+ "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
149
+ "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
150
+ "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
152
+ "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
153
+ "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
154
+ "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
156
+ "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
157
+ "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00002.bin",
158
+ "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00002.bin",
159
+ "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
160
+ "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
161
+ "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
162
+ "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
163
+ "transformer.h.20.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
164
+ "transformer.h.20.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
165
+ "transformer.h.20.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
166
+ "transformer.h.20.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
167
+ "transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
168
+ "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
169
+ "transformer.h.20.ln_2.bias": "pytorch_model-00001-of-00002.bin",
170
+ "transformer.h.20.ln_2.weight": "pytorch_model-00001-of-00002.bin",
171
+ "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
172
+ "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
173
+ "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
174
+ "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
175
+ "transformer.h.21.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
176
+ "transformer.h.21.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
177
+ "transformer.h.21.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
178
+ "transformer.h.21.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
179
+ "transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
180
+ "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
181
+ "transformer.h.21.ln_2.bias": "pytorch_model-00001-of-00002.bin",
182
+ "transformer.h.21.ln_2.weight": "pytorch_model-00001-of-00002.bin",
183
+ "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
184
+ "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
185
+ "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
186
+ "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
187
+ "transformer.h.22.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
188
+ "transformer.h.22.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
189
+ "transformer.h.22.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
190
+ "transformer.h.22.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
191
+ "transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
192
+ "transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
193
+ "transformer.h.22.ln_2.bias": "pytorch_model-00001-of-00002.bin",
194
+ "transformer.h.22.ln_2.weight": "pytorch_model-00001-of-00002.bin",
195
+ "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
196
+ "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
197
+ "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
198
+ "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
199
+ "transformer.h.23.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
200
+ "transformer.h.23.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
201
+ "transformer.h.23.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
202
+ "transformer.h.23.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
203
+ "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
204
+ "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
205
+ "transformer.h.23.ln_2.bias": "pytorch_model-00001-of-00002.bin",
206
+ "transformer.h.23.ln_2.weight": "pytorch_model-00001-of-00002.bin",
207
+ "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
208
+ "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
209
+ "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
210
+ "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
211
+ "transformer.h.24.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
212
+ "transformer.h.24.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
213
+ "transformer.h.24.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
214
+ "transformer.h.24.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
215
+ "transformer.h.24.ln_1.bias": "pytorch_model-00001-of-00002.bin",
216
+ "transformer.h.24.ln_1.weight": "pytorch_model-00001-of-00002.bin",
217
+ "transformer.h.24.ln_2.bias": "pytorch_model-00001-of-00002.bin",
218
+ "transformer.h.24.ln_2.weight": "pytorch_model-00001-of-00002.bin",
219
+ "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
220
+ "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
221
+ "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
222
+ "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
223
+ "transformer.h.25.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
224
+ "transformer.h.25.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
225
+ "transformer.h.25.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
226
+ "transformer.h.25.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
227
+ "transformer.h.25.ln_1.bias": "pytorch_model-00001-of-00002.bin",
228
+ "transformer.h.25.ln_1.weight": "pytorch_model-00001-of-00002.bin",
229
+ "transformer.h.25.ln_2.bias": "pytorch_model-00001-of-00002.bin",
230
+ "transformer.h.25.ln_2.weight": "pytorch_model-00001-of-00002.bin",
231
+ "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
232
+ "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
233
+ "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
234
+ "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
235
+ "transformer.h.26.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
236
+ "transformer.h.26.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
237
+ "transformer.h.26.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
238
+ "transformer.h.26.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
239
+ "transformer.h.26.ln_1.bias": "pytorch_model-00001-of-00002.bin",
240
+ "transformer.h.26.ln_1.weight": "pytorch_model-00001-of-00002.bin",
241
+ "transformer.h.26.ln_2.bias": "pytorch_model-00001-of-00002.bin",
242
+ "transformer.h.26.ln_2.weight": "pytorch_model-00001-of-00002.bin",
243
+ "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
244
+ "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
245
+ "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
246
+ "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
247
+ "transformer.h.27.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
248
+ "transformer.h.27.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
249
+ "transformer.h.27.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
250
+ "transformer.h.27.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
251
+ "transformer.h.27.ln_1.bias": "pytorch_model-00001-of-00002.bin",
252
+ "transformer.h.27.ln_1.weight": "pytorch_model-00001-of-00002.bin",
253
+ "transformer.h.27.ln_2.bias": "pytorch_model-00001-of-00002.bin",
254
+ "transformer.h.27.ln_2.weight": "pytorch_model-00001-of-00002.bin",
255
+ "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
256
+ "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
257
+ "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
258
+ "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
259
+ "transformer.h.28.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
260
+ "transformer.h.28.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
261
+ "transformer.h.28.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
262
+ "transformer.h.28.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
263
+ "transformer.h.28.ln_1.bias": "pytorch_model-00002-of-00002.bin",
264
+ "transformer.h.28.ln_1.weight": "pytorch_model-00002-of-00002.bin",
265
+ "transformer.h.28.ln_2.bias": "pytorch_model-00002-of-00002.bin",
266
+ "transformer.h.28.ln_2.weight": "pytorch_model-00002-of-00002.bin",
267
+ "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
268
+ "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
269
+ "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
270
+ "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
271
+ "transformer.h.29.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
272
+ "transformer.h.29.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
273
+ "transformer.h.29.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
274
+ "transformer.h.29.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
275
+ "transformer.h.29.ln_1.bias": "pytorch_model-00002-of-00002.bin",
276
+ "transformer.h.29.ln_1.weight": "pytorch_model-00002-of-00002.bin",
277
+ "transformer.h.29.ln_2.bias": "pytorch_model-00002-of-00002.bin",
278
+ "transformer.h.29.ln_2.weight": "pytorch_model-00002-of-00002.bin",
279
+ "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
280
+ "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
281
+ "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
282
+ "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
283
+ "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
284
+ "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
285
+ "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
286
+ "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
287
+ "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
288
+ "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
289
+ "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00002.bin",
290
+ "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00002.bin",
291
+ "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
292
+ "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
293
+ "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
294
+ "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "transformer.h.30.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
296
+ "transformer.h.30.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
297
+ "transformer.h.30.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
298
+ "transformer.h.30.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
299
+ "transformer.h.30.ln_1.bias": "pytorch_model-00002-of-00002.bin",
300
+ "transformer.h.30.ln_1.weight": "pytorch_model-00002-of-00002.bin",
301
+ "transformer.h.30.ln_2.bias": "pytorch_model-00002-of-00002.bin",
302
+ "transformer.h.30.ln_2.weight": "pytorch_model-00002-of-00002.bin",
303
+ "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
304
+ "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
305
+ "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
306
+ "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
307
+ "transformer.h.31.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
308
+ "transformer.h.31.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
309
+ "transformer.h.31.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
310
+ "transformer.h.31.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
311
+ "transformer.h.31.ln_1.bias": "pytorch_model-00002-of-00002.bin",
312
+ "transformer.h.31.ln_1.weight": "pytorch_model-00002-of-00002.bin",
313
+ "transformer.h.31.ln_2.bias": "pytorch_model-00002-of-00002.bin",
314
+ "transformer.h.31.ln_2.weight": "pytorch_model-00002-of-00002.bin",
315
+ "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
316
+ "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
317
+ "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
318
+ "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
319
+ "transformer.h.32.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
320
+ "transformer.h.32.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
321
+ "transformer.h.32.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
322
+ "transformer.h.32.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
323
+ "transformer.h.32.ln_1.bias": "pytorch_model-00002-of-00002.bin",
324
+ "transformer.h.32.ln_1.weight": "pytorch_model-00002-of-00002.bin",
325
+ "transformer.h.32.ln_2.bias": "pytorch_model-00002-of-00002.bin",
326
+ "transformer.h.32.ln_2.weight": "pytorch_model-00002-of-00002.bin",
327
+ "transformer.h.32.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
328
+ "transformer.h.32.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
329
+ "transformer.h.32.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
330
+ "transformer.h.32.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
331
+ "transformer.h.33.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
332
+ "transformer.h.33.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
333
+ "transformer.h.33.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
334
+ "transformer.h.33.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
335
+ "transformer.h.33.ln_1.bias": "pytorch_model-00002-of-00002.bin",
336
+ "transformer.h.33.ln_1.weight": "pytorch_model-00002-of-00002.bin",
337
+ "transformer.h.33.ln_2.bias": "pytorch_model-00002-of-00002.bin",
338
+ "transformer.h.33.ln_2.weight": "pytorch_model-00002-of-00002.bin",
339
+ "transformer.h.33.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
340
+ "transformer.h.33.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
341
+ "transformer.h.33.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
342
+ "transformer.h.33.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
343
+ "transformer.h.34.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
344
+ "transformer.h.34.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
345
+ "transformer.h.34.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
346
+ "transformer.h.34.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
347
+ "transformer.h.34.ln_1.bias": "pytorch_model-00002-of-00002.bin",
348
+ "transformer.h.34.ln_1.weight": "pytorch_model-00002-of-00002.bin",
349
+ "transformer.h.34.ln_2.bias": "pytorch_model-00002-of-00002.bin",
350
+ "transformer.h.34.ln_2.weight": "pytorch_model-00002-of-00002.bin",
351
+ "transformer.h.34.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
352
+ "transformer.h.34.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
353
+ "transformer.h.34.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
354
+ "transformer.h.34.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
355
+ "transformer.h.35.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
356
+ "transformer.h.35.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
357
+ "transformer.h.35.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
358
+ "transformer.h.35.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
359
+ "transformer.h.35.ln_1.bias": "pytorch_model-00002-of-00002.bin",
360
+ "transformer.h.35.ln_1.weight": "pytorch_model-00002-of-00002.bin",
361
+ "transformer.h.35.ln_2.bias": "pytorch_model-00002-of-00002.bin",
362
+ "transformer.h.35.ln_2.weight": "pytorch_model-00002-of-00002.bin",
363
+ "transformer.h.35.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
364
+ "transformer.h.35.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
365
+ "transformer.h.35.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
366
+ "transformer.h.35.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
367
+ "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
368
+ "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
369
+ "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
370
+ "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
371
+ "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
372
+ "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
373
+ "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00002.bin",
374
+ "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00002.bin",
375
+ "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
376
+ "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
377
+ "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
378
+ "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
379
+ "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
380
+ "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
381
+ "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
382
+ "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
383
+ "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
384
+ "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
385
+ "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00002.bin",
386
+ "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00002.bin",
387
+ "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
388
+ "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
389
+ "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
390
+ "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
391
+ "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
392
+ "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
393
+ "transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
394
+ "transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
395
+ "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
396
+ "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
397
+ "transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00002.bin",
398
+ "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00002.bin",
399
+ "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
400
+ "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
401
+ "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
402
+ "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
403
+ "transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
404
+ "transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
405
+ "transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
406
+ "transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
407
+ "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
408
+ "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
409
+ "transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00002.bin",
410
+ "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00002.bin",
411
+ "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
412
+ "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
413
+ "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
414
+ "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
415
+ "transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
416
+ "transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
417
+ "transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
418
+ "transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
419
+ "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
420
+ "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
421
+ "transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00002.bin",
422
+ "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00002.bin",
423
+ "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
424
+ "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
425
+ "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
426
+ "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
427
+ "transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
428
+ "transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
429
+ "transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
430
+ "transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
431
+ "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
432
+ "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
433
+ "transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00002.bin",
434
+ "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00002.bin",
435
+ "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
436
+ "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
437
+ "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
438
+ "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
439
+ "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
440
+ "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
441
+ "transformer.wpe.weight": "pytorch_model-00001-of-00002.bin",
442
+ "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
443
+ }
444
+ }
runs/Feb01_13-23-27_0015bb284346/events.out.tfevents.1706793989.0015bb284346.3654.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bf3266afb06a36c7aab61840ec0cbd0b20326d3ee50c5ad5bd48d5cb17b88f6
3
+ size 201604
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "eos_token": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "pad_token": {
38
+ "content": "[PAD]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<|endoftext|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<filename>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<gh_stars>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<issue_start>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_comment>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_closed>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<jupyter_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_text>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_code>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_output>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<empty_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<commit_before>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<commit_msg>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "17": {
141
+ "content": "<commit_after>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "18": {
149
+ "content": "<reponame>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49152": {
157
+ "content": "[PAD]",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ }
164
+ },
165
+ "additional_special_tokens": [
166
+ "<|endoftext|>",
167
+ "<fim_prefix>",
168
+ "<fim_middle>",
169
+ "<fim_suffix>",
170
+ "<fim_pad>",
171
+ "<filename>",
172
+ "<gh_stars>",
173
+ "<issue_start>",
174
+ "<issue_comment>",
175
+ "<issue_closed>",
176
+ "<jupyter_start>",
177
+ "<jupyter_text>",
178
+ "<jupyter_code>",
179
+ "<jupyter_output>",
180
+ "<empty_output>",
181
+ "<commit_before>",
182
+ "<commit_msg>",
183
+ "<commit_after>",
184
+ "<reponame>"
185
+ ],
186
+ "bos_token": "<|endoftext|>",
187
+ "clean_up_tokenization_spaces": true,
188
+ "eos_token": "<|endoftext|>",
189
+ "model_max_length": 8192,
190
+ "pad_token": "[PAD]",
191
+ "padding_side": "right",
192
+ "tokenizer_class": "GPT2Tokenizer",
193
+ "unk_token": "<|endoftext|>",
194
+ "vocab_size": 49152
195
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17ca5bec31d1fea8d90cd79341777007e407d67f6adc2ae80ce3033ce86bf09d
3
+ size 4792
vocab.json ADDED
The diff for this file is too large to render. See raw diff