xyd123 commited on
Commit
a362a82
1 Parent(s): 443d650
added_tokens.json DELETED
@@ -1,5 +0,0 @@
1
- {
2
- "<|endoftext|>": 151643,
3
- "<|im_end|>": 151645,
4
- "<|im_start|>": 151644
5
- }
 
 
 
 
 
 
config.json DELETED
@@ -1,28 +0,0 @@
1
- {
2
- "_name_or_path": "zjunlp/OceanGPT-14B-v0.1",
3
- "architectures": [
4
- "Qwen2ForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "eos_token_id": 151645,
9
- "hidden_act": "silu",
10
- "hidden_size": 5120,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 13696,
13
- "max_position_embeddings": 32768,
14
- "max_window_layers": 35,
15
- "model_type": "qwen2",
16
- "num_attention_heads": 40,
17
- "num_hidden_layers": 40,
18
- "num_key_value_heads": 40,
19
- "rms_norm_eps": 1e-06,
20
- "rope_theta": 1000000.0,
21
- "sliding_window": 32768,
22
- "tie_word_embeddings": false,
23
- "torch_dtype": "bfloat16",
24
- "transformers_version": "4.40.2",
25
- "use_cache": true,
26
- "use_sliding_window": false,
27
- "vocab_size": 152064
28
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "repetition_penalty": 1.05,
10
- "temperature": 0.7,
11
- "top_k": 20,
12
- "top_p": 0.8,
13
- "transformers_version": "4.40.2"
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:31def49f306b33f0e47e12dbf214a41b8a60e53f18fd1d31a703a37f17469ae0
3
- size 4919426680
 
 
 
 
model-00002-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca26b5a2b3cb9ea0563d3271d8d8d067a12b4ded894b21df094e1ac2d45b7b6b
3
- size 4991642256
 
 
 
 
model-00003-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:77b7dbb7bfbf8e3cd74719e085df8e886225c10013bb2eee094801e8a1116677
3
- size 4991631960
 
 
 
 
model-00004-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:711209a6bdd7f92de6abdbac72ec3682bd239a6bc021e08effb9634f3a974420
3
- size 4991631960
 
 
 
 
model-00005-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:773843ee4a806ea2c5d9f98a4e516efefcb8c67b82473deb1698ee8fa9f8985d
3
- size 4991631960
 
 
 
 
model-00006-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:29e283702455e40f736182fd7239763ebba87b6867ac0f3e3395393c2e63f28f
3
- size 3448672536
 
 
 
 
model.safetensors.index.json DELETED
@@ -1,490 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 28334581760
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00006-of-00006.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
14
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
15
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
16
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
17
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
18
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
19
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
20
- "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
21
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
22
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
23
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
24
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
25
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
26
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
27
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
28
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
29
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
30
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
31
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
32
- "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
33
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
34
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
35
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
36
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
37
- "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
38
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
39
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
40
- "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
41
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
42
- "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
43
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
44
- "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
45
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
46
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
47
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
48
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
49
- "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
50
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
51
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
52
- "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
53
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
54
- "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
55
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
56
- "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
57
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
58
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
59
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
60
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
61
- "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
62
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
63
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
64
- "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
65
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
66
- "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
67
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
68
- "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
69
- "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
70
- "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
71
- "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
72
- "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
73
- "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
74
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
75
- "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
76
- "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
77
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
78
- "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
79
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
80
- "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
81
- "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
82
- "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
83
- "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
84
- "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
85
- "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
86
- "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
87
- "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
88
- "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
89
- "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
90
- "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
91
- "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
92
- "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
93
- "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
94
- "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
95
- "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
96
- "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
97
- "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
98
- "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
99
- "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
100
- "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
101
- "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
102
- "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
103
- "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
104
- "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
105
- "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
106
- "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
107
- "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
108
- "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
109
- "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
110
- "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
111
- "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
112
- "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
113
- "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
114
- "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
115
- "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
116
- "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
117
- "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
118
- "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
119
- "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
120
- "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
121
- "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
122
- "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
123
- "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
124
- "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
125
- "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
126
- "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
127
- "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
128
- "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
129
- "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
130
- "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
131
- "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
132
- "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
133
- "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
134
- "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
135
- "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
136
- "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
137
- "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
138
- "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
139
- "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
140
- "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
141
- "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
142
- "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
143
- "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
144
- "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
145
- "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
146
- "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
147
- "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
148
- "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
149
- "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
150
- "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
151
- "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
152
- "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
153
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
154
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
155
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
156
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
157
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
158
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
159
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
160
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
161
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
162
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
163
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
164
- "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
165
- "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
166
- "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
167
- "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
168
- "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
169
- "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
170
- "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
171
- "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
172
- "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
173
- "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
174
- "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
175
- "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
176
- "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
177
- "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
178
- "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
179
- "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
180
- "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
181
- "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
182
- "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
183
- "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
184
- "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
185
- "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
186
- "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
187
- "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
188
- "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
189
- "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
190
- "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
191
- "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
192
- "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
193
- "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
194
- "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
195
- "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
196
- "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
197
- "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
198
- "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
199
- "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
200
- "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
201
- "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
202
- "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
203
- "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
204
- "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
205
- "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
206
- "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
207
- "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
208
- "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
209
- "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
210
- "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
211
- "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
212
- "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
213
- "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
214
- "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
215
- "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
216
- "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
217
- "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
218
- "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
219
- "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
220
- "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
221
- "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
222
- "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
223
- "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
224
- "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
225
- "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
226
- "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
227
- "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
228
- "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
229
- "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
230
- "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
231
- "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
232
- "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
233
- "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
234
- "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
235
- "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
236
- "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
237
- "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
238
- "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
239
- "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
240
- "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
241
- "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
242
- "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
243
- "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
244
- "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
245
- "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
246
- "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
247
- "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
248
- "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
249
- "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
250
- "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
251
- "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
252
- "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
253
- "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
254
- "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
255
- "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
256
- "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
257
- "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
258
- "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
259
- "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
260
- "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
261
- "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
262
- "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
263
- "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
264
- "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
265
- "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
266
- "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
267
- "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
268
- "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
269
- "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
270
- "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
271
- "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
272
- "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
273
- "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
274
- "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
275
- "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
276
- "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
277
- "model.layers.29.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
278
- "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
279
- "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
280
- "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
281
- "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
282
- "model.layers.29.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
283
- "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
284
- "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
285
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
286
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
287
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
288
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
289
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
290
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
291
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
292
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
293
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
294
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
295
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
296
- "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
297
- "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
298
- "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
299
- "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
300
- "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
301
- "model.layers.30.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
302
- "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
303
- "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
304
- "model.layers.30.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
305
- "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
306
- "model.layers.30.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
307
- "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
308
- "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
309
- "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
310
- "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
311
- "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
312
- "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
313
- "model.layers.31.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
314
- "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
315
- "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
316
- "model.layers.31.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
317
- "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
318
- "model.layers.31.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
319
- "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
320
- "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
321
- "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
322
- "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
323
- "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
324
- "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
325
- "model.layers.32.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
326
- "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
327
- "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
328
- "model.layers.32.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
329
- "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
330
- "model.layers.32.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
331
- "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
332
- "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
333
- "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
334
- "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
335
- "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
336
- "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
337
- "model.layers.33.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
338
- "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
339
- "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
340
- "model.layers.33.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
341
- "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
342
- "model.layers.33.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
343
- "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
344
- "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
345
- "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
346
- "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
347
- "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
348
- "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
349
- "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
350
- "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
351
- "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
352
- "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
353
- "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
354
- "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
355
- "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
356
- "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
357
- "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
358
- "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
359
- "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
360
- "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
361
- "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
362
- "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
363
- "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
364
- "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
365
- "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
366
- "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
367
- "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
368
- "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
369
- "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
370
- "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
371
- "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
372
- "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
373
- "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
374
- "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
375
- "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
376
- "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
377
- "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
378
- "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
379
- "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
380
- "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
381
- "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
382
- "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
383
- "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
384
- "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
385
- "model.layers.37.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
386
- "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
387
- "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
388
- "model.layers.37.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
389
- "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
390
- "model.layers.37.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
391
- "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
392
- "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
393
- "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
394
- "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
395
- "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
396
- "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
397
- "model.layers.38.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
398
- "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
399
- "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
400
- "model.layers.38.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
401
- "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
402
- "model.layers.38.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
403
- "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
404
- "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
405
- "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
406
- "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
407
- "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
408
- "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
409
- "model.layers.39.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
410
- "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
411
- "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
412
- "model.layers.39.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
413
- "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
414
- "model.layers.39.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
415
- "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
416
- "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
417
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
418
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
419
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
420
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
421
- "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
422
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
423
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
424
- "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
425
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
426
- "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
427
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
428
- "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
429
- "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
430
- "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
431
- "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
432
- "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
433
- "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
434
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
435
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
436
- "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
437
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
438
- "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
439
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
440
- "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
441
- "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
442
- "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
443
- "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
444
- "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
445
- "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
446
- "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
447
- "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
448
- "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
449
- "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
450
- "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
451
- "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
452
- "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
453
- "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
454
- "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
455
- "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
456
- "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
457
- "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
458
- "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
459
- "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
460
- "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
461
- "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
462
- "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
463
- "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
464
- "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
465
- "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
466
- "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
467
- "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
468
- "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
469
- "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
470
- "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
471
- "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
472
- "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
473
- "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
474
- "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
475
- "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
476
- "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
477
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
478
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
479
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
480
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
481
- "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
482
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
483
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
484
- "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
485
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
486
- "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
487
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
488
- "model.norm.weight": "model-00006-of-00006.safetensors"
489
- }
490
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json DELETED
@@ -1,20 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>"
5
- ],
6
- "eos_token": {
7
- "content": "<|im_end|>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false
12
- },
13
- "pad_token": {
14
- "content": "<|endoftext|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false
19
- }
20
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json DELETED
@@ -1,43 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "151643": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "151644": {
13
- "content": "<|im_start|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "151645": {
21
- "content": "<|im_end|>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- }
28
- },
29
- "additional_special_tokens": [
30
- "<|im_start|>",
31
- "<|im_end|>"
32
- ],
33
- "bos_token": null,
34
- "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
- "clean_up_tokenization_spaces": false,
36
- "eos_token": "<|im_end|>",
37
- "errors": "replace",
38
- "model_max_length": 32768,
39
- "pad_token": "<|endoftext|>",
40
- "split_special_tokens": false,
41
- "tokenizer_class": "Qwen2Tokenizer",
42
- "unk_token": null
43
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vocab.json DELETED
The diff for this file is too large to render. See raw diff