satpalsr commited on
Commit
6e609aa
1 Parent(s): 1ceda3a

End of training

Browse files
README.md ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/phi-2
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: phi2-filter2
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<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)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.3.0`
19
+ ```yaml
20
+ base_model: microsoft/phi-2
21
+ model_type: AutoModelForCausalLM
22
+ tokenizer_type: AutoTokenizer
23
+ trust_remote_code: true
24
+
25
+ load_in_8bit: false
26
+ load_in_4bit: false
27
+ strict: false
28
+
29
+ hub_model_id: satpalsr/phi2-filter2
30
+ hf_use_auth_token: true
31
+
32
+ datasets:
33
+ - path: satpalsr/translation-filter
34
+ type: completion
35
+
36
+ dataset_prepared_path:
37
+ val_set_size: 0.01
38
+ output_dir: ./phi-sft-out2
39
+
40
+ sequence_len: 2048
41
+ sample_packing: false # currently unsupported
42
+ pad_to_sequence_len:
43
+
44
+ adapter:
45
+ lora_model_dir:
46
+ lora_r: 16
47
+ lora_alpha: 32
48
+ lora_dropout: 0.1
49
+ lora_target_linear: true
50
+ lora_fan_in_fan_out:
51
+ lora_modules_to_save:
52
+ - embd
53
+ - lm_head
54
+
55
+ wandb_project: phi2transfilter
56
+ wandb_entity:
57
+ wandb_watch:
58
+ wandb_name:
59
+ wandb_log_model:
60
+
61
+ gradient_accumulation_steps: 1
62
+ micro_batch_size: 16
63
+ num_epochs: 4
64
+ optimizer: paged_adamw_8bit
65
+ adam_beta2: 0.95
66
+ adam_epsilon: 0.00001
67
+ max_grad_norm: 1.0
68
+ lr_scheduler: cosine
69
+ learning_rate: 1e-5
70
+
71
+ train_on_inputs: false
72
+ group_by_length: false
73
+ bf16: true
74
+ fp16: false
75
+ tf32: true
76
+
77
+ gradient_checkpointing: true
78
+ early_stopping_patience:
79
+ resume_from_checkpoint:
80
+ local_rank:
81
+ logging_steps: 1
82
+ xformers_attention:
83
+ flash_attention: false
84
+
85
+ warmup_steps: 100
86
+ evals_per_epoch: 4
87
+ saves_per_epoch: 1
88
+ debug:
89
+ deepspeed:
90
+ weight_decay: 0.1
91
+ fsdp:
92
+ fsdp_config:
93
+ resize_token_embeddings_to_32x: true
94
+ special_tokens:
95
+ pad_token: "<|endoftext|>"
96
+ ```
97
+
98
+ </details><br>
99
+
100
+ # phi2-filter2
101
+
102
+ This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
103
+ It achieves the following results on the evaluation set:
104
+ - Loss: 0.1944
105
+
106
+ ## Model description
107
+
108
+ More information needed
109
+
110
+ ## Intended uses & limitations
111
+
112
+ More information needed
113
+
114
+ ## Training and evaluation data
115
+
116
+ More information needed
117
+
118
+ ## Training procedure
119
+
120
+ ### Training hyperparameters
121
+
122
+ The following hyperparameters were used during training:
123
+ - learning_rate: 1e-05
124
+ - train_batch_size: 16
125
+ - eval_batch_size: 16
126
+ - seed: 42
127
+ - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
128
+ - lr_scheduler_type: cosine
129
+ - lr_scheduler_warmup_steps: 100
130
+ - num_epochs: 4
131
+
132
+ ### Training results
133
+
134
+ | Training Loss | Epoch | Step | Validation Loss |
135
+ |:-------------:|:-----:|:----:|:---------------:|
136
+ | 2.5676 | 0.01 | 1 | 2.5391 |
137
+ | 2.4364 | 0.25 | 29 | 2.4042 |
138
+ | 1.9523 | 0.5 | 58 | 1.8580 |
139
+ | 1.1137 | 0.75 | 87 | 0.9535 |
140
+ | 0.5107 | 1.0 | 116 | 0.4195 |
141
+ | 0.4588 | 1.25 | 145 | 0.2877 |
142
+ | 0.2876 | 1.5 | 174 | 0.2462 |
143
+ | 0.2959 | 1.75 | 203 | 0.2264 |
144
+ | 0.2197 | 2.0 | 232 | 0.2114 |
145
+ | 0.3045 | 2.25 | 261 | 0.2052 |
146
+ | 0.2726 | 2.5 | 290 | 0.2022 |
147
+ | 0.3046 | 2.75 | 319 | 0.1975 |
148
+ | 0.3316 | 3.0 | 348 | 0.1954 |
149
+ | 0.2223 | 3.25 | 377 | 0.1950 |
150
+ | 0.2609 | 3.5 | 406 | 0.1946 |
151
+ | 0.2739 | 3.75 | 435 | 0.1945 |
152
+ | 0.2703 | 4.0 | 464 | 0.1944 |
153
+
154
+
155
+ ### Framework versions
156
+
157
+ - Transformers 4.37.0.dev0
158
+ - Pytorch 2.1.1+cu118
159
+ - Datasets 2.16.1
160
+ - Tokenizers 0.15.0
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.37.0.dev0"
4
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75091de45c232b1a101e95e4c95097d13507d96473d9211e2c7b31d5ede7cf9d
3
+ size 4982664536
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2d6ef2f8a88b10bf4080c010b5ef3ec3e75f76502122ea8e53a849886a4d7db
3
+ size 1101481480
model.safetensors.index.json ADDED
@@ -0,0 +1,460 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6084096000
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "model-00002-of-00002.safetensors",
7
+ "lm_head.weight": "model-00002-of-00002.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.final_layernorm.bias": "model-00002-of-00002.safetensors",
10
+ "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
11
+ "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
34
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
38
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
46
+ "model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
48
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
50
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
52
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
56
+ "model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
58
+ "model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
60
+ "model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
62
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
64
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
68
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
70
+ "model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
72
+ "model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
74
+ "model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
76
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
80
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
82
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
84
+ "model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
86
+ "model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
88
+ "model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
92
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
94
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
96
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
98
+ "model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
100
+ "model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
104
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
106
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
108
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
110
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
112
+ "model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
116
+ "model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
118
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
120
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
122
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
124
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
128
+ "model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
130
+ "model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
132
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
134
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
136
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
140
+ "model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
142
+ "model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
144
+ "model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
146
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
148
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
152
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
154
+ "model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
156
+ "model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
158
+ "model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
160
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
164
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
166
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
168
+ "model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
170
+ "model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
172
+ "model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
174
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
176
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
178
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
180
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
182
+ "model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
184
+ "model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
186
+ "model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
188
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
190
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
192
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
194
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
196
+ "model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
198
+ "model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
200
+ "model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
202
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
204
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
206
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
208
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
210
+ "model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
212
+ "model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
214
+ "model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
216
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
218
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
220
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
222
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
224
+ "model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
226
+ "model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
228
+ "model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
230
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
232
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
234
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
236
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
238
+ "model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
240
+ "model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
242
+ "model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
244
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
246
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
248
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
250
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
252
+ "model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
254
+ "model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
256
+ "model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
258
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
260
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
262
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
264
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
266
+ "model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
268
+ "model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
270
+ "model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
272
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
274
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
276
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
278
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
280
+ "model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
282
+ "model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
284
+ "model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
286
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
288
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
290
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
292
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
296
+ "model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
297
+ "model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
298
+ "model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
300
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
301
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
302
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
304
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.28.input_layernorm.bias": "model-00002-of-00002.safetensors",
306
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.28.mlp.fc1.bias": "model-00002-of-00002.safetensors",
308
+ "model.layers.28.mlp.fc1.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.28.mlp.fc2.bias": "model-00002-of-00002.safetensors",
310
+ "model.layers.28.mlp.fc2.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
312
+ "model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
314
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
315
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
316
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
317
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
318
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.29.input_layernorm.bias": "model-00002-of-00002.safetensors",
320
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.29.mlp.fc1.bias": "model-00002-of-00002.safetensors",
322
+ "model.layers.29.mlp.fc1.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.29.mlp.fc2.bias": "model-00002-of-00002.safetensors",
324
+ "model.layers.29.mlp.fc2.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.29.self_attn.dense.bias": "model-00002-of-00002.safetensors",
326
+ "model.layers.29.self_attn.dense.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
328
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
330
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
332
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
334
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
336
+ "model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
338
+ "model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
340
+ "model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
342
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
344
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
346
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
347
+ "model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
348
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
350
+ "model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
352
+ "model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
354
+ "model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
356
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
358
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
360
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
362
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
364
+ "model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
366
+ "model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
368
+ "model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
369
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
370
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
371
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
372
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
373
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
374
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
375
+ "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
380
+ "model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
382
+ "model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
384
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
386
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
388
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
392
+ "model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
394
+ "model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
396
+ "model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
398
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
400
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
402
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
404
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
406
+ "model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
408
+ "model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
410
+ "model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
412
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
414
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
416
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
418
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
420
+ "model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
422
+ "model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
424
+ "model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
426
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
428
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
430
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
432
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
434
+ "model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
436
+ "model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
438
+ "model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
440
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
442
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
444
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
446
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
448
+ "model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
450
+ "model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
451
+ "model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
452
+ "model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
454
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
456
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
458
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
459
+ }
460
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e732db0b389321c4f26f043715a6078ef2e5f992ae7983e045807094ffbdd11c
3
+ size 4982760277
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a16103d781a8aed4cbc4dc5d35790261bf929b389f3c1627c03b35920eb5f120
3
+ size 1101494098
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,460 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6084096000
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "pytorch_model-00002-of-00002.bin",
7
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
8
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.final_layernorm.bias": "pytorch_model-00002-of-00002.bin",
10
+ "model.final_layernorm.weight": "pytorch_model-00002-of-00002.bin",
11
+ "model.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.0.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.0.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.1.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.1.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.10.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.10.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.11.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.11.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.12.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.12.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.13.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.13.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
89
+ "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
90
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.layers.14.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
102
+ "model.layers.14.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
106
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
107
+ "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
108
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
110
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
112
+ "model.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
114
+ "model.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.layers.15.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
116
+ "model.layers.15.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
117
+ "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
120
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
124
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
125
+ "model.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
126
+ "model.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
128
+ "model.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
129
+ "model.layers.16.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
130
+ "model.layers.16.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
132
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
134
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
135
+ "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
136
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "model.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
138
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
139
+ "model.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
140
+ "model.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
141
+ "model.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
142
+ "model.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
143
+ "model.layers.17.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
144
+ "model.layers.17.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
145
+ "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
146
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
147
+ "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
148
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
153
+ "model.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
154
+ "model.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
155
+ "model.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
156
+ "model.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
157
+ "model.layers.18.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
158
+ "model.layers.18.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
159
+ "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
160
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
162
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
163
+ "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
164
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
165
+ "model.layers.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
166
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
167
+ "model.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
168
+ "model.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
169
+ "model.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
170
+ "model.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
171
+ "model.layers.19.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
172
+ "model.layers.19.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
173
+ "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
174
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
175
+ "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
176
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
177
+ "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
178
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
179
+ "model.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
180
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
181
+ "model.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
182
+ "model.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
183
+ "model.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
184
+ "model.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
185
+ "model.layers.2.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
186
+ "model.layers.2.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
187
+ "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
188
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
189
+ "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
190
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
191
+ "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
192
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
193
+ "model.layers.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
194
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
195
+ "model.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
196
+ "model.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
197
+ "model.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
198
+ "model.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
199
+ "model.layers.20.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
200
+ "model.layers.20.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
201
+ "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
202
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
203
+ "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
204
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
205
+ "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
206
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
207
+ "model.layers.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
208
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
209
+ "model.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
210
+ "model.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
211
+ "model.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
212
+ "model.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
213
+ "model.layers.21.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
214
+ "model.layers.21.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
215
+ "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
216
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
218
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
219
+ "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
220
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "model.layers.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
222
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
223
+ "model.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
224
+ "model.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
225
+ "model.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
226
+ "model.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
227
+ "model.layers.22.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
228
+ "model.layers.22.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
229
+ "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
230
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
231
+ "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
232
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
233
+ "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
234
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
235
+ "model.layers.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
236
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
237
+ "model.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
238
+ "model.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
239
+ "model.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
240
+ "model.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
241
+ "model.layers.23.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
242
+ "model.layers.23.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
243
+ "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
244
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
246
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
247
+ "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
248
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
249
+ "model.layers.24.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
250
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
251
+ "model.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
252
+ "model.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
253
+ "model.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
254
+ "model.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
255
+ "model.layers.24.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
256
+ "model.layers.24.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
257
+ "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
258
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
259
+ "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
260
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
261
+ "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
262
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
263
+ "model.layers.25.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
264
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
265
+ "model.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
266
+ "model.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
267
+ "model.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
268
+ "model.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
269
+ "model.layers.25.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
270
+ "model.layers.25.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
271
+ "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
272
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
273
+ "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
274
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
276
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
277
+ "model.layers.26.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
278
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
279
+ "model.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
280
+ "model.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
281
+ "model.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
282
+ "model.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
283
+ "model.layers.26.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
284
+ "model.layers.26.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
285
+ "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
286
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
287
+ "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
288
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
289
+ "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
290
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "model.layers.27.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
292
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
293
+ "model.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
294
+ "model.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
295
+ "model.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
296
+ "model.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
297
+ "model.layers.27.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
298
+ "model.layers.27.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
299
+ "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
300
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
301
+ "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
302
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
303
+ "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
304
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
305
+ "model.layers.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
306
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
307
+ "model.layers.28.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
308
+ "model.layers.28.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
309
+ "model.layers.28.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
310
+ "model.layers.28.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
311
+ "model.layers.28.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
312
+ "model.layers.28.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
313
+ "model.layers.28.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
314
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
315
+ "model.layers.28.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
316
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
317
+ "model.layers.28.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
318
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
319
+ "model.layers.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
320
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
321
+ "model.layers.29.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
322
+ "model.layers.29.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
323
+ "model.layers.29.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
324
+ "model.layers.29.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
325
+ "model.layers.29.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin",
326
+ "model.layers.29.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin",
327
+ "model.layers.29.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
328
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
329
+ "model.layers.29.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
330
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
331
+ "model.layers.29.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
332
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
333
+ "model.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
334
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
335
+ "model.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
336
+ "model.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
337
+ "model.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
338
+ "model.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
339
+ "model.layers.3.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
340
+ "model.layers.3.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
341
+ "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
342
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
343
+ "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
344
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
345
+ "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
346
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
347
+ "model.layers.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
348
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
349
+ "model.layers.30.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
350
+ "model.layers.30.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
351
+ "model.layers.30.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
352
+ "model.layers.30.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
353
+ "model.layers.30.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin",
354
+ "model.layers.30.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin",
355
+ "model.layers.30.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
356
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
357
+ "model.layers.30.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
358
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
359
+ "model.layers.30.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
360
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
361
+ "model.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
362
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
363
+ "model.layers.31.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
364
+ "model.layers.31.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
365
+ "model.layers.31.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
366
+ "model.layers.31.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
367
+ "model.layers.31.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin",
368
+ "model.layers.31.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin",
369
+ "model.layers.31.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
370
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
371
+ "model.layers.31.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
372
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
373
+ "model.layers.31.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
374
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
375
+ "model.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
376
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
377
+ "model.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
378
+ "model.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
379
+ "model.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
380
+ "model.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
381
+ "model.layers.4.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
382
+ "model.layers.4.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
383
+ "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
384
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
385
+ "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
386
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
387
+ "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
388
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
389
+ "model.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
390
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
391
+ "model.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
392
+ "model.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
393
+ "model.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
394
+ "model.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
395
+ "model.layers.5.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
396
+ "model.layers.5.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
397
+ "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
398
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
399
+ "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
400
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
401
+ "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
402
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
403
+ "model.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
404
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
405
+ "model.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
406
+ "model.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
407
+ "model.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
408
+ "model.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
409
+ "model.layers.6.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
410
+ "model.layers.6.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
411
+ "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
412
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
413
+ "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
414
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
415
+ "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
416
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
417
+ "model.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
418
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
419
+ "model.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
420
+ "model.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
421
+ "model.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
422
+ "model.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
423
+ "model.layers.7.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
424
+ "model.layers.7.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
425
+ "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
426
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
427
+ "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
428
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
429
+ "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
430
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
431
+ "model.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
432
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
433
+ "model.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
434
+ "model.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
435
+ "model.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
436
+ "model.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
437
+ "model.layers.8.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
438
+ "model.layers.8.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
439
+ "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
440
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
441
+ "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
442
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
443
+ "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
444
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
445
+ "model.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
446
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
447
+ "model.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
448
+ "model.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
449
+ "model.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
450
+ "model.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
451
+ "model.layers.9.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
452
+ "model.layers.9.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
453
+ "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
454
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
455
+ "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
456
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
457
+ "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
458
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin"
459
+ }
460
+ }