hllj commited on
Commit
8992381
1 Parent(s): 89a6525

Upload model

Browse files
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen-7B",
3
+ "architectures": [
4
+ "QWenLMHeadModel"
5
+ ],
6
+ "attn_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "Qwen/Qwen-7B--configuration_qwen.QWenConfig",
9
+ "AutoModelForCausalLM": "Qwen/Qwen-7B--modeling_qwen.QWenLMHeadModel"
10
+ },
11
+ "bf16": true,
12
+ "emb_dropout_prob": 0.0,
13
+ "fp16": false,
14
+ "fp32": false,
15
+ "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 22016,
18
+ "kv_channels": 128,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "max_position_embeddings": 32768,
21
+ "model_type": "qwen",
22
+ "no_bias": true,
23
+ "num_attention_heads": 32,
24
+ "num_hidden_layers": 32,
25
+ "onnx_safe": null,
26
+ "rotary_emb_base": 10000,
27
+ "rotary_pct": 1.0,
28
+ "scale_attn_weights": true,
29
+ "seq_length": 8192,
30
+ "softmax_in_fp32": false,
31
+ "tie_word_embeddings": false,
32
+ "tokenizer_class": "QWenTokenizer",
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.36.2",
35
+ "use_cache": true,
36
+ "use_cache_kernel": false,
37
+ "use_cache_quantization": false,
38
+ "use_dynamic_ntk": true,
39
+ "use_flash_attn": true,
40
+ "use_logn_attn": true,
41
+ "vocab_size": 151936
42
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chat_format": "raw",
3
+ "do_sample": true,
4
+ "eos_token_id": 151643,
5
+ "max_new_tokens": 512,
6
+ "pad_token_id": 151643,
7
+ "stop_words_ids": [
8
+ [
9
+ 151643
10
+ ]
11
+ ],
12
+ "top_k": 0,
13
+ "top_p": 0.8,
14
+ "transformers_version": "4.36.2"
15
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d76d008945bc753b3faee04f10bb864259e5527c56ba65cd4fd2da85fd4e76
3
+ size 4988485656
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb975d8b2bc98cf70d9855dab81ea5e7c96ed20b14dab52fcbef940b195ba05f
3
+ size 4981246520
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e25aabc59aca2522640fd20a51f1e64c94b59ec59ca1a1ed66aedc4eb52db63
3
+ size 4228285288
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59f06d357bab4958e48382cf0d22198a3dc811116a414dbad45564aa154bb329
3
+ size 1244659840
model.safetensors.index.json ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15442649088
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "transformer.h.0.attn.c_attn.bias": "model-00001-of-00004.safetensors",
8
+ "transformer.h.0.attn.c_attn.weight": "model-00001-of-00004.safetensors",
9
+ "transformer.h.0.attn.c_proj.weight": "model-00001-of-00004.safetensors",
10
+ "transformer.h.0.ln_1.weight": "model-00001-of-00004.safetensors",
11
+ "transformer.h.0.ln_2.weight": "model-00001-of-00004.safetensors",
12
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
13
+ "transformer.h.0.mlp.w1.weight": "model-00001-of-00004.safetensors",
14
+ "transformer.h.0.mlp.w2.weight": "model-00001-of-00004.safetensors",
15
+ "transformer.h.1.attn.c_attn.bias": "model-00001-of-00004.safetensors",
16
+ "transformer.h.1.attn.c_attn.weight": "model-00001-of-00004.safetensors",
17
+ "transformer.h.1.attn.c_proj.weight": "model-00001-of-00004.safetensors",
18
+ "transformer.h.1.ln_1.weight": "model-00001-of-00004.safetensors",
19
+ "transformer.h.1.ln_2.weight": "model-00001-of-00004.safetensors",
20
+ "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
21
+ "transformer.h.1.mlp.w1.weight": "model-00001-of-00004.safetensors",
22
+ "transformer.h.1.mlp.w2.weight": "model-00001-of-00004.safetensors",
23
+ "transformer.h.10.attn.c_attn.bias": "model-00002-of-00004.safetensors",
24
+ "transformer.h.10.attn.c_attn.weight": "model-00002-of-00004.safetensors",
25
+ "transformer.h.10.attn.c_proj.weight": "model-00002-of-00004.safetensors",
26
+ "transformer.h.10.ln_1.weight": "model-00002-of-00004.safetensors",
27
+ "transformer.h.10.ln_2.weight": "model-00002-of-00004.safetensors",
28
+ "transformer.h.10.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
29
+ "transformer.h.10.mlp.w1.weight": "model-00002-of-00004.safetensors",
30
+ "transformer.h.10.mlp.w2.weight": "model-00002-of-00004.safetensors",
31
+ "transformer.h.11.attn.c_attn.bias": "model-00002-of-00004.safetensors",
32
+ "transformer.h.11.attn.c_attn.weight": "model-00002-of-00004.safetensors",
33
+ "transformer.h.11.attn.c_proj.weight": "model-00002-of-00004.safetensors",
34
+ "transformer.h.11.ln_1.weight": "model-00002-of-00004.safetensors",
35
+ "transformer.h.11.ln_2.weight": "model-00002-of-00004.safetensors",
36
+ "transformer.h.11.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
37
+ "transformer.h.11.mlp.w1.weight": "model-00002-of-00004.safetensors",
38
+ "transformer.h.11.mlp.w2.weight": "model-00002-of-00004.safetensors",
39
+ "transformer.h.12.attn.c_attn.bias": "model-00002-of-00004.safetensors",
40
+ "transformer.h.12.attn.c_attn.weight": "model-00002-of-00004.safetensors",
41
+ "transformer.h.12.attn.c_proj.weight": "model-00002-of-00004.safetensors",
42
+ "transformer.h.12.ln_1.weight": "model-00002-of-00004.safetensors",
43
+ "transformer.h.12.ln_2.weight": "model-00002-of-00004.safetensors",
44
+ "transformer.h.12.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
45
+ "transformer.h.12.mlp.w1.weight": "model-00002-of-00004.safetensors",
46
+ "transformer.h.12.mlp.w2.weight": "model-00002-of-00004.safetensors",
47
+ "transformer.h.13.attn.c_attn.bias": "model-00002-of-00004.safetensors",
48
+ "transformer.h.13.attn.c_attn.weight": "model-00002-of-00004.safetensors",
49
+ "transformer.h.13.attn.c_proj.weight": "model-00002-of-00004.safetensors",
50
+ "transformer.h.13.ln_1.weight": "model-00002-of-00004.safetensors",
51
+ "transformer.h.13.ln_2.weight": "model-00002-of-00004.safetensors",
52
+ "transformer.h.13.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
53
+ "transformer.h.13.mlp.w1.weight": "model-00002-of-00004.safetensors",
54
+ "transformer.h.13.mlp.w2.weight": "model-00002-of-00004.safetensors",
55
+ "transformer.h.14.attn.c_attn.bias": "model-00002-of-00004.safetensors",
56
+ "transformer.h.14.attn.c_attn.weight": "model-00002-of-00004.safetensors",
57
+ "transformer.h.14.attn.c_proj.weight": "model-00002-of-00004.safetensors",
58
+ "transformer.h.14.ln_1.weight": "model-00002-of-00004.safetensors",
59
+ "transformer.h.14.ln_2.weight": "model-00002-of-00004.safetensors",
60
+ "transformer.h.14.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
61
+ "transformer.h.14.mlp.w1.weight": "model-00002-of-00004.safetensors",
62
+ "transformer.h.14.mlp.w2.weight": "model-00002-of-00004.safetensors",
63
+ "transformer.h.15.attn.c_attn.bias": "model-00002-of-00004.safetensors",
64
+ "transformer.h.15.attn.c_attn.weight": "model-00002-of-00004.safetensors",
65
+ "transformer.h.15.attn.c_proj.weight": "model-00002-of-00004.safetensors",
66
+ "transformer.h.15.ln_1.weight": "model-00002-of-00004.safetensors",
67
+ "transformer.h.15.ln_2.weight": "model-00002-of-00004.safetensors",
68
+ "transformer.h.15.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
69
+ "transformer.h.15.mlp.w1.weight": "model-00002-of-00004.safetensors",
70
+ "transformer.h.15.mlp.w2.weight": "model-00002-of-00004.safetensors",
71
+ "transformer.h.16.attn.c_attn.bias": "model-00002-of-00004.safetensors",
72
+ "transformer.h.16.attn.c_attn.weight": "model-00002-of-00004.safetensors",
73
+ "transformer.h.16.attn.c_proj.weight": "model-00002-of-00004.safetensors",
74
+ "transformer.h.16.ln_1.weight": "model-00002-of-00004.safetensors",
75
+ "transformer.h.16.ln_2.weight": "model-00002-of-00004.safetensors",
76
+ "transformer.h.16.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
77
+ "transformer.h.16.mlp.w1.weight": "model-00002-of-00004.safetensors",
78
+ "transformer.h.16.mlp.w2.weight": "model-00002-of-00004.safetensors",
79
+ "transformer.h.17.attn.c_attn.bias": "model-00002-of-00004.safetensors",
80
+ "transformer.h.17.attn.c_attn.weight": "model-00002-of-00004.safetensors",
81
+ "transformer.h.17.attn.c_proj.weight": "model-00002-of-00004.safetensors",
82
+ "transformer.h.17.ln_1.weight": "model-00002-of-00004.safetensors",
83
+ "transformer.h.17.ln_2.weight": "model-00002-of-00004.safetensors",
84
+ "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
85
+ "transformer.h.17.mlp.w1.weight": "model-00002-of-00004.safetensors",
86
+ "transformer.h.17.mlp.w2.weight": "model-00002-of-00004.safetensors",
87
+ "transformer.h.18.attn.c_attn.bias": "model-00002-of-00004.safetensors",
88
+ "transformer.h.18.attn.c_attn.weight": "model-00002-of-00004.safetensors",
89
+ "transformer.h.18.attn.c_proj.weight": "model-00002-of-00004.safetensors",
90
+ "transformer.h.18.ln_1.weight": "model-00002-of-00004.safetensors",
91
+ "transformer.h.18.ln_2.weight": "model-00002-of-00004.safetensors",
92
+ "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
93
+ "transformer.h.18.mlp.w1.weight": "model-00002-of-00004.safetensors",
94
+ "transformer.h.18.mlp.w2.weight": "model-00002-of-00004.safetensors",
95
+ "transformer.h.19.attn.c_attn.bias": "model-00002-of-00004.safetensors",
96
+ "transformer.h.19.attn.c_attn.weight": "model-00002-of-00004.safetensors",
97
+ "transformer.h.19.attn.c_proj.weight": "model-00002-of-00004.safetensors",
98
+ "transformer.h.19.ln_1.weight": "model-00002-of-00004.safetensors",
99
+ "transformer.h.19.ln_2.weight": "model-00002-of-00004.safetensors",
100
+ "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
101
+ "transformer.h.19.mlp.w1.weight": "model-00002-of-00004.safetensors",
102
+ "transformer.h.19.mlp.w2.weight": "model-00002-of-00004.safetensors",
103
+ "transformer.h.2.attn.c_attn.bias": "model-00001-of-00004.safetensors",
104
+ "transformer.h.2.attn.c_attn.weight": "model-00001-of-00004.safetensors",
105
+ "transformer.h.2.attn.c_proj.weight": "model-00001-of-00004.safetensors",
106
+ "transformer.h.2.ln_1.weight": "model-00001-of-00004.safetensors",
107
+ "transformer.h.2.ln_2.weight": "model-00001-of-00004.safetensors",
108
+ "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
109
+ "transformer.h.2.mlp.w1.weight": "model-00001-of-00004.safetensors",
110
+ "transformer.h.2.mlp.w2.weight": "model-00001-of-00004.safetensors",
111
+ "transformer.h.20.attn.c_attn.bias": "model-00002-of-00004.safetensors",
112
+ "transformer.h.20.attn.c_attn.weight": "model-00002-of-00004.safetensors",
113
+ "transformer.h.20.attn.c_proj.weight": "model-00002-of-00004.safetensors",
114
+ "transformer.h.20.ln_1.weight": "model-00002-of-00004.safetensors",
115
+ "transformer.h.20.ln_2.weight": "model-00002-of-00004.safetensors",
116
+ "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
117
+ "transformer.h.20.mlp.w1.weight": "model-00002-of-00004.safetensors",
118
+ "transformer.h.20.mlp.w2.weight": "model-00002-of-00004.safetensors",
119
+ "transformer.h.21.attn.c_attn.bias": "model-00002-of-00004.safetensors",
120
+ "transformer.h.21.attn.c_attn.weight": "model-00002-of-00004.safetensors",
121
+ "transformer.h.21.attn.c_proj.weight": "model-00002-of-00004.safetensors",
122
+ "transformer.h.21.ln_1.weight": "model-00002-of-00004.safetensors",
123
+ "transformer.h.21.ln_2.weight": "model-00002-of-00004.safetensors",
124
+ "transformer.h.21.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
125
+ "transformer.h.21.mlp.w1.weight": "model-00002-of-00004.safetensors",
126
+ "transformer.h.21.mlp.w2.weight": "model-00003-of-00004.safetensors",
127
+ "transformer.h.22.attn.c_attn.bias": "model-00003-of-00004.safetensors",
128
+ "transformer.h.22.attn.c_attn.weight": "model-00003-of-00004.safetensors",
129
+ "transformer.h.22.attn.c_proj.weight": "model-00003-of-00004.safetensors",
130
+ "transformer.h.22.ln_1.weight": "model-00003-of-00004.safetensors",
131
+ "transformer.h.22.ln_2.weight": "model-00003-of-00004.safetensors",
132
+ "transformer.h.22.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
133
+ "transformer.h.22.mlp.w1.weight": "model-00003-of-00004.safetensors",
134
+ "transformer.h.22.mlp.w2.weight": "model-00003-of-00004.safetensors",
135
+ "transformer.h.23.attn.c_attn.bias": "model-00003-of-00004.safetensors",
136
+ "transformer.h.23.attn.c_attn.weight": "model-00003-of-00004.safetensors",
137
+ "transformer.h.23.attn.c_proj.weight": "model-00003-of-00004.safetensors",
138
+ "transformer.h.23.ln_1.weight": "model-00003-of-00004.safetensors",
139
+ "transformer.h.23.ln_2.weight": "model-00003-of-00004.safetensors",
140
+ "transformer.h.23.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
141
+ "transformer.h.23.mlp.w1.weight": "model-00003-of-00004.safetensors",
142
+ "transformer.h.23.mlp.w2.weight": "model-00003-of-00004.safetensors",
143
+ "transformer.h.24.attn.c_attn.bias": "model-00003-of-00004.safetensors",
144
+ "transformer.h.24.attn.c_attn.weight": "model-00003-of-00004.safetensors",
145
+ "transformer.h.24.attn.c_proj.weight": "model-00003-of-00004.safetensors",
146
+ "transformer.h.24.ln_1.weight": "model-00003-of-00004.safetensors",
147
+ "transformer.h.24.ln_2.weight": "model-00003-of-00004.safetensors",
148
+ "transformer.h.24.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
149
+ "transformer.h.24.mlp.w1.weight": "model-00003-of-00004.safetensors",
150
+ "transformer.h.24.mlp.w2.weight": "model-00003-of-00004.safetensors",
151
+ "transformer.h.25.attn.c_attn.bias": "model-00003-of-00004.safetensors",
152
+ "transformer.h.25.attn.c_attn.weight": "model-00003-of-00004.safetensors",
153
+ "transformer.h.25.attn.c_proj.weight": "model-00003-of-00004.safetensors",
154
+ "transformer.h.25.ln_1.weight": "model-00003-of-00004.safetensors",
155
+ "transformer.h.25.ln_2.weight": "model-00003-of-00004.safetensors",
156
+ "transformer.h.25.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
157
+ "transformer.h.25.mlp.w1.weight": "model-00003-of-00004.safetensors",
158
+ "transformer.h.25.mlp.w2.weight": "model-00003-of-00004.safetensors",
159
+ "transformer.h.26.attn.c_attn.bias": "model-00003-of-00004.safetensors",
160
+ "transformer.h.26.attn.c_attn.weight": "model-00003-of-00004.safetensors",
161
+ "transformer.h.26.attn.c_proj.weight": "model-00003-of-00004.safetensors",
162
+ "transformer.h.26.ln_1.weight": "model-00003-of-00004.safetensors",
163
+ "transformer.h.26.ln_2.weight": "model-00003-of-00004.safetensors",
164
+ "transformer.h.26.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
165
+ "transformer.h.26.mlp.w1.weight": "model-00003-of-00004.safetensors",
166
+ "transformer.h.26.mlp.w2.weight": "model-00003-of-00004.safetensors",
167
+ "transformer.h.27.attn.c_attn.bias": "model-00003-of-00004.safetensors",
168
+ "transformer.h.27.attn.c_attn.weight": "model-00003-of-00004.safetensors",
169
+ "transformer.h.27.attn.c_proj.weight": "model-00003-of-00004.safetensors",
170
+ "transformer.h.27.ln_1.weight": "model-00003-of-00004.safetensors",
171
+ "transformer.h.27.ln_2.weight": "model-00003-of-00004.safetensors",
172
+ "transformer.h.27.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
173
+ "transformer.h.27.mlp.w1.weight": "model-00003-of-00004.safetensors",
174
+ "transformer.h.27.mlp.w2.weight": "model-00003-of-00004.safetensors",
175
+ "transformer.h.28.attn.c_attn.bias": "model-00003-of-00004.safetensors",
176
+ "transformer.h.28.attn.c_attn.weight": "model-00003-of-00004.safetensors",
177
+ "transformer.h.28.attn.c_proj.weight": "model-00003-of-00004.safetensors",
178
+ "transformer.h.28.ln_1.weight": "model-00003-of-00004.safetensors",
179
+ "transformer.h.28.ln_2.weight": "model-00003-of-00004.safetensors",
180
+ "transformer.h.28.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
181
+ "transformer.h.28.mlp.w1.weight": "model-00003-of-00004.safetensors",
182
+ "transformer.h.28.mlp.w2.weight": "model-00003-of-00004.safetensors",
183
+ "transformer.h.29.attn.c_attn.bias": "model-00003-of-00004.safetensors",
184
+ "transformer.h.29.attn.c_attn.weight": "model-00003-of-00004.safetensors",
185
+ "transformer.h.29.attn.c_proj.weight": "model-00003-of-00004.safetensors",
186
+ "transformer.h.29.ln_1.weight": "model-00003-of-00004.safetensors",
187
+ "transformer.h.29.ln_2.weight": "model-00003-of-00004.safetensors",
188
+ "transformer.h.29.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
189
+ "transformer.h.29.mlp.w1.weight": "model-00003-of-00004.safetensors",
190
+ "transformer.h.29.mlp.w2.weight": "model-00003-of-00004.safetensors",
191
+ "transformer.h.3.attn.c_attn.bias": "model-00001-of-00004.safetensors",
192
+ "transformer.h.3.attn.c_attn.weight": "model-00001-of-00004.safetensors",
193
+ "transformer.h.3.attn.c_proj.weight": "model-00001-of-00004.safetensors",
194
+ "transformer.h.3.ln_1.weight": "model-00001-of-00004.safetensors",
195
+ "transformer.h.3.ln_2.weight": "model-00001-of-00004.safetensors",
196
+ "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
197
+ "transformer.h.3.mlp.w1.weight": "model-00001-of-00004.safetensors",
198
+ "transformer.h.3.mlp.w2.weight": "model-00001-of-00004.safetensors",
199
+ "transformer.h.30.attn.c_attn.bias": "model-00003-of-00004.safetensors",
200
+ "transformer.h.30.attn.c_attn.weight": "model-00003-of-00004.safetensors",
201
+ "transformer.h.30.attn.c_proj.weight": "model-00003-of-00004.safetensors",
202
+ "transformer.h.30.ln_1.weight": "model-00003-of-00004.safetensors",
203
+ "transformer.h.30.ln_2.weight": "model-00003-of-00004.safetensors",
204
+ "transformer.h.30.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
205
+ "transformer.h.30.mlp.w1.weight": "model-00003-of-00004.safetensors",
206
+ "transformer.h.30.mlp.w2.weight": "model-00003-of-00004.safetensors",
207
+ "transformer.h.31.attn.c_attn.bias": "model-00003-of-00004.safetensors",
208
+ "transformer.h.31.attn.c_attn.weight": "model-00003-of-00004.safetensors",
209
+ "transformer.h.31.attn.c_proj.weight": "model-00003-of-00004.safetensors",
210
+ "transformer.h.31.ln_1.weight": "model-00003-of-00004.safetensors",
211
+ "transformer.h.31.ln_2.weight": "model-00003-of-00004.safetensors",
212
+ "transformer.h.31.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
213
+ "transformer.h.31.mlp.w1.weight": "model-00003-of-00004.safetensors",
214
+ "transformer.h.31.mlp.w2.weight": "model-00003-of-00004.safetensors",
215
+ "transformer.h.4.attn.c_attn.bias": "model-00001-of-00004.safetensors",
216
+ "transformer.h.4.attn.c_attn.weight": "model-00001-of-00004.safetensors",
217
+ "transformer.h.4.attn.c_proj.weight": "model-00001-of-00004.safetensors",
218
+ "transformer.h.4.ln_1.weight": "model-00001-of-00004.safetensors",
219
+ "transformer.h.4.ln_2.weight": "model-00001-of-00004.safetensors",
220
+ "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
221
+ "transformer.h.4.mlp.w1.weight": "model-00001-of-00004.safetensors",
222
+ "transformer.h.4.mlp.w2.weight": "model-00001-of-00004.safetensors",
223
+ "transformer.h.5.attn.c_attn.bias": "model-00001-of-00004.safetensors",
224
+ "transformer.h.5.attn.c_attn.weight": "model-00001-of-00004.safetensors",
225
+ "transformer.h.5.attn.c_proj.weight": "model-00001-of-00004.safetensors",
226
+ "transformer.h.5.ln_1.weight": "model-00001-of-00004.safetensors",
227
+ "transformer.h.5.ln_2.weight": "model-00001-of-00004.safetensors",
228
+ "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
229
+ "transformer.h.5.mlp.w1.weight": "model-00001-of-00004.safetensors",
230
+ "transformer.h.5.mlp.w2.weight": "model-00001-of-00004.safetensors",
231
+ "transformer.h.6.attn.c_attn.bias": "model-00001-of-00004.safetensors",
232
+ "transformer.h.6.attn.c_attn.weight": "model-00001-of-00004.safetensors",
233
+ "transformer.h.6.attn.c_proj.weight": "model-00001-of-00004.safetensors",
234
+ "transformer.h.6.ln_1.weight": "model-00001-of-00004.safetensors",
235
+ "transformer.h.6.ln_2.weight": "model-00001-of-00004.safetensors",
236
+ "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
237
+ "transformer.h.6.mlp.w1.weight": "model-00001-of-00004.safetensors",
238
+ "transformer.h.6.mlp.w2.weight": "model-00001-of-00004.safetensors",
239
+ "transformer.h.7.attn.c_attn.bias": "model-00001-of-00004.safetensors",
240
+ "transformer.h.7.attn.c_attn.weight": "model-00001-of-00004.safetensors",
241
+ "transformer.h.7.attn.c_proj.weight": "model-00001-of-00004.safetensors",
242
+ "transformer.h.7.ln_1.weight": "model-00001-of-00004.safetensors",
243
+ "transformer.h.7.ln_2.weight": "model-00001-of-00004.safetensors",
244
+ "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
245
+ "transformer.h.7.mlp.w1.weight": "model-00001-of-00004.safetensors",
246
+ "transformer.h.7.mlp.w2.weight": "model-00001-of-00004.safetensors",
247
+ "transformer.h.8.attn.c_attn.bias": "model-00001-of-00004.safetensors",
248
+ "transformer.h.8.attn.c_attn.weight": "model-00001-of-00004.safetensors",
249
+ "transformer.h.8.attn.c_proj.weight": "model-00001-of-00004.safetensors",
250
+ "transformer.h.8.ln_1.weight": "model-00001-of-00004.safetensors",
251
+ "transformer.h.8.ln_2.weight": "model-00001-of-00004.safetensors",
252
+ "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
253
+ "transformer.h.8.mlp.w1.weight": "model-00001-of-00004.safetensors",
254
+ "transformer.h.8.mlp.w2.weight": "model-00001-of-00004.safetensors",
255
+ "transformer.h.9.attn.c_attn.bias": "model-00001-of-00004.safetensors",
256
+ "transformer.h.9.attn.c_attn.weight": "model-00001-of-00004.safetensors",
257
+ "transformer.h.9.attn.c_proj.weight": "model-00002-of-00004.safetensors",
258
+ "transformer.h.9.ln_1.weight": "model-00001-of-00004.safetensors",
259
+ "transformer.h.9.ln_2.weight": "model-00002-of-00004.safetensors",
260
+ "transformer.h.9.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
261
+ "transformer.h.9.mlp.w1.weight": "model-00002-of-00004.safetensors",
262
+ "transformer.h.9.mlp.w2.weight": "model-00002-of-00004.safetensors",
263
+ "transformer.ln_f.weight": "model-00003-of-00004.safetensors",
264
+ "transformer.wte.weight": "model-00001-of-00004.safetensors"
265
+ }
266
+ }