Hugging Face's logo

CarperAI
/
stable-vicuna-13b-delta

Text Generation
Transformers
PyTorch
English
llama
causal-lm
Inference Endpoints
text-generation-inference
Model card Files Community
9
jon-tow commited on
Commit
045e4f8
•
1 Parent(s): 90c0bd3

refactor(readme): transfer naming

Browse files
Files changed (8) hide show
  1. .gitattributes +0 -34
  2. README.md +0 -54
  3. config.json +0 -23
  4. generation_config.json +0 -7
  5. pytorch_model-00001-of-00003.bin +0 -3
  6. pytorch_model-00002-of-00003.bin +0 -3
  7. pytorch_model-00003-of-00003.bin +0 -3
  8. pytorch_model.bin.index.json +0 -410
.gitattributes DELETED
@@ -1,34 +0,0 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tflite filter=lfs diff=lfs merge=lfs -text
29
- *.tgz filter=lfs diff=lfs merge=lfs -text
30
- *.wasm filter=lfs diff=lfs merge=lfs -text
31
- *.xz filter=lfs diff=lfs merge=lfs -text
32
- *.zip filter=lfs diff=lfs merge=lfs -text
33
- *.zst filter=lfs diff=lfs merge=lfs -text
34
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
README.md DELETED
@@ -1,54 +0,0 @@
1
- Apply Delta weights
2
-
3
- ```python
4
-
5
- """
6
- Usage:
7
- python3 apply_delta.py --base /path/to/model_weights/llama-13b --target stable-vicuna-13b --delta pvduy/stable-vicuna-13b-delta
8
- """
9
- import argparse
10
-
11
- import torch
12
- from tqdm import tqdm
13
- from transformers import AutoTokenizer, AutoModelForCausalLM
14
-
15
-
16
- def apply_delta(base_model_path, target_model_path, delta_path):
17
- print("Loading base model")
18
- base = AutoModelForCausalLM.from_pretrained(
19
- base_model_path, torch_dtype=torch.float16, low_cpu_mem_usage=True)
20
-
21
- print("Loading delta")
22
- delta = AutoModelForCausalLM.from_pretrained(delta_path, torch_dtype=torch.float16, low_cpu_mem_usage=True)
23
- delta_tokenizer = AutoTokenizer.from_pretrained(delta_path)
24
-
25
- DEFAULT_PAD_TOKEN = "[PAD]"
26
- base_tokenizer = AutoTokenizer.from_pretrained(base_model_path, use_fast=False)
27
- num_new_tokens = base_tokenizer.add_special_tokens(dict(pad_token=DEFAULT_PAD_TOKEN))
28
-
29
- base.resize_token_embeddings(len(base_tokenizer))
30
- input_embeddings = base.get_input_embeddings().weight.data
31
- output_embeddings = base.get_output_embeddings().weight.data
32
- input_embeddings[-num_new_tokens:] = 0
33
- output_embeddings[-num_new_tokens:] = 0
34
-
35
- print("Applying delta")
36
- for name, param in tqdm(base.state_dict().items(), desc="Applying delta"):
37
- assert name in delta.state_dict()
38
- param.data += delta.state_dict()[name]
39
-
40
- print("Saving target model")
41
- base.save_pretrained(target_model_path)
42
- delta_tokenizer.save_pretrained(target_model_path)
43
-
44
-
45
- if __name__ == "__main__":
46
- parser = argparse.ArgumentParser()
47
- parser.add_argument("--base-model-path", type=str, required=True)
48
- parser.add_argument("--target-model-path", type=str, required=True)
49
- parser.add_argument("--delta-path", type=str, required=True)
50
-
51
- args = parser.parse_args()
52
-
53
- apply_delta(args.base_model_path, args.target_model_path, args.delta_path)
54
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "_name_or_path": "CarperAI/vicuna-13b-fine-tuned-rlhf",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "bos_token_id": 1,
7
- "eos_token_id": 2,
8
- "hidden_act": "silu",
9
- "hidden_size": 5120,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 13824,
12
- "max_position_embeddings": 2048,
13
- "model_type": "llama",
14
- "num_attention_heads": 40,
15
- "num_hidden_layers": 40,
16
- "pad_token_id": 0,
17
- "rms_norm_eps": 1e-06,
18
- "tie_word_embeddings": false,
19
- "torch_dtype": "float16",
20
- "transformers_version": "4.28.0.dev0",
21
- "use_cache": true,
22
- "vocab_size": 32001
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.28.0.dev0"
7
- }
 
 
 
 
 
 
 
 
pytorch_model-00001-of-00003.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1c013c8bb3d13df0947deba75fd121158dca2003bf84e84d339fd5a7679e626
3
- size 9948736750
 
 
 
 
pytorch_model-00002-of-00003.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:97a58e98726dc7dc1fa1f9b61c77289b103447b1d02829d48937d61ab51ae8b5
3
- size 9904162976
 
 
 
 
pytorch_model-00003-of-00003.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d3259c387715d327c2c0521370fcf1470fcdcd1221b17d2ebfd6d3ddae9cb9e
3
- size 6178992713
 
 
 
 
pytorch_model.bin.index.json DELETED
@@ -1,410 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 26031754240
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
- "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
- "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
- "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
- "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
- "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
- "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
- "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
- "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
- "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
- "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
- "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
18
- "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
- "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
20
- "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
21
- "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
22
- "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
- "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
24
- "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
25
- "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
26
- "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
27
- "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
28
- "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
29
- "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
30
- "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
31
- "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
32
- "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
33
- "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
- "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
35
- "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
36
- "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
37
- "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
- "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
39
- "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
40
- "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
41
- "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
42
- "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
43
- "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
44
- "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
45
- "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
46
- "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
- "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
48
- "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
- "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
50
- "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
51
- "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
52
- "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
53
- "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
54
- "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
55
- "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
56
- "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
57
- "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
58
- "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
59
- "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
60
- "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
61
- "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
62
- "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
63
- "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
64
- "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
65
- "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
66
- "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
67
- "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
68
- "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
69
- "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
70
- "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
71
- "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
72
- "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
73
- "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
74
- "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
75
- "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
76
- "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
77
- "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
78
- "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
- "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
80
- "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
81
- "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
82
- "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
83
- "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
84
- "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
85
- "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
86
- "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
87
- "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
88
- "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
89
- "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
90
- "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
91
- "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
92
- "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
- "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
- "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
95
- "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
96
- "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
97
- "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
- "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
- "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
- "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
- "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
- "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
- "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
- "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
- "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
- "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
- "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
108
- "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
- "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
- "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
- "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
- "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
- "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
- "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
- "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
- "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
117
- "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
118
- "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
- "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
120
- "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
121
- "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
122
- "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
123
- "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
124
- "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
125
- "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
126
- "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
127
- "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
128
- "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
129
- "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
130
- "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
131
- "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
132
- "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
133
- "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
134
- "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
135
- "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
136
- "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
137
- "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
138
- "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
- "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
140
- "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
141
- "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
- "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
- "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
144
- "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
145
- "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
146
- "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
147
- "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
148
- "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
149
- "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
150
- "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
151
- "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
152
- "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
- "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
154
- "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
155
- "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
156
- "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
157
- "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
158
- "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
- "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
160
- "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
161
- "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
162
- "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
163
- "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
164
- "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
165
- "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
166
- "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
- "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
168
- "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
169
- "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
170
- "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
171
- "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
172
- "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
173
- "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
174
- "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
175
- "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
176
- "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
177
- "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
178
- "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
179
- "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
180
- "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
181
- "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
182
- "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
183
- "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
184
- "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
185
- "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
186
- "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
187
- "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
188
- "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
189
- "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
190
- "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
191
- "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
192
- "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
193
- "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
194
- "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
195
- "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
196
- "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
197
- "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
198
- "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
199
- "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
200
- "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
201
- "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
202
- "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
203
- "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
204
- "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
205
- "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
206
- "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
207
- "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
208
- "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
209
- "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
210
- "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
211
- "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
212
- "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
213
- "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
214
- "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
215
- "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
216
- "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
217
- "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
218
- "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
219
- "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
220
- "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
221
- "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
222
- "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
223
- "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
224
- "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
225
- "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
226
- "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
227
- "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
228
- "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
229
- "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
230
- "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
231
- "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
232
- "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
233
- "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
234
- "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
235
- "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
236
- "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
237
- "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
238
- "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
239
- "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
240
- "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
241
- "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
242
- "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
- "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
244
- "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
245
- "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
246
- "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
247
- "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
248
- "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
249
- "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
250
- "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
251
- "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
252
- "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
253
- "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
254
- "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
255
- "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
256
- "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
257
- "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
258
- "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
259
- "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
260
- "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
261
- "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
262
- "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
263
- "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
264
- "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
265
- "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
266
- "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
267
- "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
268
- "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
269
- "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
270
- "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
271
- "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
272
- "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
273
- "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
274
- "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
275
- "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
276
- "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
277
- "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
278
- "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
279
- "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
280
- "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
281
- "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
282
- "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
283
- "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
284
- "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
285
- "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
286
- "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
287
- "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
288
- "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
289
- "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
290
- "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
291
- "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
292
- "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
293
- "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
294
- "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
295
- "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
296
- "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
297
- "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
298
- "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
299
- "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
300
- "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
301
- "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
302
- "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
303
- "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
304
- "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
305
- "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
306
- "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
307
- "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
308
- "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
309
- "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
310
- "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
311
- "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
312
- "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
313
- "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
314
- "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
315
- "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
316
- "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
317
- "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
318
- "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
319
- "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
320
- "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
321
- "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
322
- "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
323
- "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
324
- "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
325
- "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
326
- "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
327
- "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
328
- "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
329
- "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
330
- "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
331
- "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
332
- "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
333
- "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
334
- "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
335
- "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
336
- "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
337
- "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
338
- "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
339
- "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
340
- "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
341
- "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
342
- "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
343
- "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
344
- "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
345
- "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
346
- "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
347
- "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
348
- "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
349
- "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
350
- "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
351
- "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
352
- "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
353
- "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
354
- "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
355
- "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
356
- "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
357
- "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
358
- "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
359
- "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
360
- "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
361
- "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
362
- "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
363
- "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
364
- "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
365
- "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
366
- "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
367
- "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
368
- "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
369
- "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
370
- "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
371
- "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
372
- "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
373
- "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
374
- "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
375
- "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
376
- "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
377
- "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
378
- "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
379
- "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
380
- "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
381
- "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
382
- "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
383
- "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
384
- "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
385
- "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
386
- "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
387
- "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
388
- "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
389
- "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
390
- "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
391
- "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
392
- "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
393
- "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
394
- "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
395
- "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
396
- "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
397
- "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
398
- "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
399
- "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
400
- "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
401
- "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
402
- "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
403
- "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
404
- "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
405
- "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
406
- "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
407
- "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
408
- "model.norm.weight": "pytorch_model-00003-of-00003.bin"
409
- }
410
- }