sperfu commited on
Commit
940bfd4
1 Parent(s): afcb041
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pretrain_model/Qwen1.5-14B-Chat",
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": "float16",
24
+ "transformers_version": "4.41.2",
25
+ "use_cache": true,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 152064
28
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "4.41.2"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f09dfe17c3579d86cbd3f5f4e0aebdf21ec9d8c33416299908a52c3b347fb327
3
+ size 1907132301
pytorch_model-00002-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e9ef224eba19a39466f2f4f30109a1c115a05228013f9a26f5aa7244994f346
3
+ size 1891535474
pytorch_model-00003-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4ec4e1a044008ac6389287da90052af561e3fcd902e5a646fdac45f7c98fada
3
+ size 1891535474
pytorch_model-00004-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5e3f87fa9fa072c667d8ec8f9feeb04270606ea74cba41de5dceae83e664316
3
+ size 1891535474
pytorch_model-00005-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b305e81f198bf5041cdfc42d07c2aebc69f0edae736a6a8b7cc05d5ca5dcf081
3
+ size 1891535474
pytorch_model-00006-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36298d477084edde43af44ffb4de6a96a6a78c897c060331a1db0c4bc38f936d
3
+ size 1891535474
pytorch_model-00007-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9d7cb976ce39cb5786f7ea93ddf2dc4155ffa6999340c191a80a9872898fd7b
3
+ size 1891535474
pytorch_model-00008-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:248b778deaca50826e8dbbdc562753d8ea0e0fde2fee220c9ad3a67b8c8c35e1
3
+ size 1891535474
pytorch_model-00009-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e47faf2b572597ac21a9eec4dc5474c21e0b2e7fcca02c891867d5fc658e0e90
3
+ size 1891535474
pytorch_model-00010-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727b402c2e0097fa072ffc347b95de5e9136cac70fa1b35fa319fd29205dc96d
3
+ size 1891535474
pytorch_model-00011-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03a669a35d4a9a22f46615982dd3971a79594a445803a11284cdc23cfdc3af1e
3
+ size 1891535474
pytorch_model-00012-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4567c8d525ad23ec3bacb72ded222c8aaf8b6846d395f23fd3336b86b4469edc
3
+ size 1891535474
pytorch_model-00013-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e8e049b6fce7c54a02cd876b9f135509612a1c2853a1b37612556a9bdfff8dc
3
+ size 1891535474
pytorch_model-00014-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae10a42dc31eb637d79d3469bf60fa9faa685e3d5c58fab3739b17509574a3a
3
+ size 1891535474
pytorch_model-00015-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd6855d32ec9b0c15f5acb0886f9f51ddb99b450d43f45c36eee0be46dd25bdc
3
+ size 1837663130
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,490 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 28334581760
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00015-of-00015.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
13
+ "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00015.bin",
14
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
15
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
16
+ "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00015.bin",
17
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
18
+ "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00015.bin",
19
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
20
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
21
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
22
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
23
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
24
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
25
+ "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00015.bin",
26
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
27
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
28
+ "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00015.bin",
29
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
30
+ "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00015.bin",
31
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
32
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
33
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
34
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
35
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
36
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
37
+ "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00005-of-00015.bin",
38
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
39
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
40
+ "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00005-of-00015.bin",
41
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
42
+ "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00005-of-00015.bin",
43
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
44
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
45
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
46
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
47
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
48
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
49
+ "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00005-of-00015.bin",
50
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
51
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
52
+ "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00005-of-00015.bin",
53
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
54
+ "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00005-of-00015.bin",
55
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
56
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
57
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
58
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
59
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
60
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
61
+ "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00005-of-00015.bin",
62
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
63
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
64
+ "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00005-of-00015.bin",
65
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
66
+ "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00005-of-00015.bin",
67
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
68
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
69
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
70
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
71
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
72
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
73
+ "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00006-of-00015.bin",
74
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
75
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
76
+ "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00006-of-00015.bin",
77
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
78
+ "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00006-of-00015.bin",
79
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
80
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
81
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
82
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
83
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
84
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
85
+ "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00006-of-00015.bin",
86
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
87
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
88
+ "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00006-of-00015.bin",
89
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
90
+ "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00006-of-00015.bin",
91
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
92
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
93
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
94
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
95
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
96
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
97
+ "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00006-of-00015.bin",
98
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
99
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
100
+ "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00006-of-00015.bin",
101
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
102
+ "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00006-of-00015.bin",
103
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
104
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
105
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
106
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
107
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
108
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
109
+ "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00007-of-00015.bin",
110
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
111
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
112
+ "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00007-of-00015.bin",
113
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
114
+ "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00007-of-00015.bin",
115
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
116
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
117
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
118
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
119
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
120
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
121
+ "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00007-of-00015.bin",
122
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
123
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
124
+ "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00007-of-00015.bin",
125
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
126
+ "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00007-of-00015.bin",
127
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
128
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
129
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
130
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
131
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
132
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
133
+ "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00007-of-00015.bin",
134
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
135
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
136
+ "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00007-of-00015.bin",
137
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
138
+ "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00007-of-00015.bin",
139
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
140
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
141
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
142
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
143
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
144
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
145
+ "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00008-of-00015.bin",
146
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
147
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
148
+ "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00008-of-00015.bin",
149
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
150
+ "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00008-of-00015.bin",
151
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
152
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
153
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
154
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
155
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
156
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
157
+ "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00015.bin",
158
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
159
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
160
+ "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00015.bin",
161
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
162
+ "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00015.bin",
163
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
164
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
165
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
166
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
167
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
168
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
169
+ "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00008-of-00015.bin",
170
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
171
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
172
+ "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00008-of-00015.bin",
173
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
174
+ "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00008-of-00015.bin",
175
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
176
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
177
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
178
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
179
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
180
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
181
+ "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00008-of-00015.bin",
182
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
183
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
184
+ "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00008-of-00015.bin",
185
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
186
+ "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00008-of-00015.bin",
187
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
188
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
189
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
190
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
191
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
192
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
193
+ "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00009-of-00015.bin",
194
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
195
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
196
+ "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00009-of-00015.bin",
197
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
198
+ "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00009-of-00015.bin",
199
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
200
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
201
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
202
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
203
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
204
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
205
+ "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00009-of-00015.bin",
206
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
207
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
208
+ "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00009-of-00015.bin",
209
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
210
+ "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00009-of-00015.bin",
211
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
212
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
213
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
214
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
215
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
216
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
217
+ "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00009-of-00015.bin",
218
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
219
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
220
+ "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00009-of-00015.bin",
221
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
222
+ "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00009-of-00015.bin",
223
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
224
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
225
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
226
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
227
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
228
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
229
+ "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00010-of-00015.bin",
230
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
231
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
232
+ "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00010-of-00015.bin",
233
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
234
+ "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00010-of-00015.bin",
235
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
236
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
237
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
238
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
239
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
240
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
241
+ "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00010-of-00015.bin",
242
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
243
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
244
+ "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00010-of-00015.bin",
245
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
246
+ "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00010-of-00015.bin",
247
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
248
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
249
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
250
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
251
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
252
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
253
+ "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00010-of-00015.bin",
254
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
255
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
256
+ "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00010-of-00015.bin",
257
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
258
+ "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00010-of-00015.bin",
259
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
260
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
261
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
262
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
263
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
264
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
265
+ "model.layers.28.self_attn.k_proj.bias": "pytorch_model-00011-of-00015.bin",
266
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
267
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
268
+ "model.layers.28.self_attn.q_proj.bias": "pytorch_model-00011-of-00015.bin",
269
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
270
+ "model.layers.28.self_attn.v_proj.bias": "pytorch_model-00011-of-00015.bin",
271
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
272
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
273
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
274
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
275
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
276
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
277
+ "model.layers.29.self_attn.k_proj.bias": "pytorch_model-00011-of-00015.bin",
278
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
279
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
280
+ "model.layers.29.self_attn.q_proj.bias": "pytorch_model-00011-of-00015.bin",
281
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
282
+ "model.layers.29.self_attn.v_proj.bias": "pytorch_model-00011-of-00015.bin",
283
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
284
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
285
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
286
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
287
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
288
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
289
+ "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00015.bin",
290
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
291
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
292
+ "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00015.bin",
293
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
294
+ "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00015.bin",
295
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
296
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
297
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
298
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
299
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
300
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
301
+ "model.layers.30.self_attn.k_proj.bias": "pytorch_model-00011-of-00015.bin",
302
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
303
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
304
+ "model.layers.30.self_attn.q_proj.bias": "pytorch_model-00011-of-00015.bin",
305
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
306
+ "model.layers.30.self_attn.v_proj.bias": "pytorch_model-00011-of-00015.bin",
307
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
308
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
309
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
310
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
311
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
312
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
313
+ "model.layers.31.self_attn.k_proj.bias": "pytorch_model-00012-of-00015.bin",
314
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
315
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
316
+ "model.layers.31.self_attn.q_proj.bias": "pytorch_model-00012-of-00015.bin",
317
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
318
+ "model.layers.31.self_attn.v_proj.bias": "pytorch_model-00012-of-00015.bin",
319
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
320
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
321
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
322
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
323
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
324
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
325
+ "model.layers.32.self_attn.k_proj.bias": "pytorch_model-00012-of-00015.bin",
326
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
327
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
328
+ "model.layers.32.self_attn.q_proj.bias": "pytorch_model-00012-of-00015.bin",
329
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
330
+ "model.layers.32.self_attn.v_proj.bias": "pytorch_model-00012-of-00015.bin",
331
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
332
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
333
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
334
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
335
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
336
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
337
+ "model.layers.33.self_attn.k_proj.bias": "pytorch_model-00012-of-00015.bin",
338
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
339
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
340
+ "model.layers.33.self_attn.q_proj.bias": "pytorch_model-00012-of-00015.bin",
341
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
342
+ "model.layers.33.self_attn.v_proj.bias": "pytorch_model-00012-of-00015.bin",
343
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
344
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
345
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
346
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
347
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
348
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
349
+ "model.layers.34.self_attn.k_proj.bias": "pytorch_model-00013-of-00015.bin",
350
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
351
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
352
+ "model.layers.34.self_attn.q_proj.bias": "pytorch_model-00013-of-00015.bin",
353
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
354
+ "model.layers.34.self_attn.v_proj.bias": "pytorch_model-00013-of-00015.bin",
355
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
356
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
357
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
358
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
359
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
360
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
361
+ "model.layers.35.self_attn.k_proj.bias": "pytorch_model-00013-of-00015.bin",
362
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
363
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
364
+ "model.layers.35.self_attn.q_proj.bias": "pytorch_model-00013-of-00015.bin",
365
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
366
+ "model.layers.35.self_attn.v_proj.bias": "pytorch_model-00013-of-00015.bin",
367
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
368
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
369
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
370
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
371
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
372
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
373
+ "model.layers.36.self_attn.k_proj.bias": "pytorch_model-00013-of-00015.bin",
374
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
375
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
376
+ "model.layers.36.self_attn.q_proj.bias": "pytorch_model-00013-of-00015.bin",
377
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
378
+ "model.layers.36.self_attn.v_proj.bias": "pytorch_model-00013-of-00015.bin",
379
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
380
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
381
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
382
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
383
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
384
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
385
+ "model.layers.37.self_attn.k_proj.bias": "pytorch_model-00014-of-00015.bin",
386
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
387
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
388
+ "model.layers.37.self_attn.q_proj.bias": "pytorch_model-00014-of-00015.bin",
389
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
390
+ "model.layers.37.self_attn.v_proj.bias": "pytorch_model-00014-of-00015.bin",
391
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
392
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
393
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
394
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
395
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
396
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
397
+ "model.layers.38.self_attn.k_proj.bias": "pytorch_model-00014-of-00015.bin",
398
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
399
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
400
+ "model.layers.38.self_attn.q_proj.bias": "pytorch_model-00014-of-00015.bin",
401
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
402
+ "model.layers.38.self_attn.v_proj.bias": "pytorch_model-00014-of-00015.bin",
403
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
404
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00015-of-00015.bin",
405
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin",
406
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
407
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00015-of-00015.bin",
408
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin",
409
+ "model.layers.39.self_attn.k_proj.bias": "pytorch_model-00014-of-00015.bin",
410
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
411
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
412
+ "model.layers.39.self_attn.q_proj.bias": "pytorch_model-00014-of-00015.bin",
413
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
414
+ "model.layers.39.self_attn.v_proj.bias": "pytorch_model-00014-of-00015.bin",
415
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
416
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
417
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
418
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
419
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
420
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
421
+ "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00015.bin",
422
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
423
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
424
+ "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00015.bin",
425
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
426
+ "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00015.bin",
427
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
428
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
429
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
430
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
431
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
432
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
433
+ "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00015.bin",
434
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
435
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
436
+ "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00015.bin",
437
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
438
+ "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00015.bin",
439
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
440
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
441
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
442
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
443
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
444
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
445
+ "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00015.bin",
446
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
447
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
448
+ "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00015.bin",
449
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
450
+ "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00015.bin",
451
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
452
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
453
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
454
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
455
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
456
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
457
+ "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00004-of-00015.bin",
458
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
459
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
460
+ "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00004-of-00015.bin",
461
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
462
+ "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00004-of-00015.bin",
463
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
464
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
465
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
466
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
467
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
468
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
469
+ "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00004-of-00015.bin",
470
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
471
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
472
+ "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00004-of-00015.bin",
473
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
474
+ "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00004-of-00015.bin",
475
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
476
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
477
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
478
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
479
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
480
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
481
+ "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00004-of-00015.bin",
482
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
483
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
484
+ "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00004-of-00015.bin",
485
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
486
+ "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00004-of-00015.bin",
487
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
488
+ "model.norm.weight": "pytorch_model-00015-of-00015.bin"
489
+ }
490
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
The diff for this file is too large to render. See raw diff