HenryJJ
commited on
Commit
•
93b2a35
1
Parent(s):
fc83c7a
init model
Browse files- added_tokens.json +42 -0
- config.json +34 -0
- generation_config.json +4 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +332 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +344 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"\t\t": 50294,
|
3 |
+
"\t\t\t": 50293,
|
4 |
+
"\t\t\t\t": 50292,
|
5 |
+
"\t\t\t\t\t": 50291,
|
6 |
+
"\t\t\t\t\t\t": 50290,
|
7 |
+
"\t\t\t\t\t\t\t": 50289,
|
8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
10 |
+
" ": 50286,
|
11 |
+
" ": 50285,
|
12 |
+
" ": 50284,
|
13 |
+
" ": 50283,
|
14 |
+
" ": 50282,
|
15 |
+
" ": 50281,
|
16 |
+
" ": 50280,
|
17 |
+
" ": 50279,
|
18 |
+
" ": 50278,
|
19 |
+
" ": 50277,
|
20 |
+
" ": 50276,
|
21 |
+
" ": 50275,
|
22 |
+
" ": 50274,
|
23 |
+
" ": 50273,
|
24 |
+
" ": 50272,
|
25 |
+
" ": 50271,
|
26 |
+
" ": 50270,
|
27 |
+
" ": 50269,
|
28 |
+
" ": 50268,
|
29 |
+
" ": 50267,
|
30 |
+
" ": 50266,
|
31 |
+
" ": 50265,
|
32 |
+
" ": 50264,
|
33 |
+
" ": 50263,
|
34 |
+
" ": 50262,
|
35 |
+
" ": 50261,
|
36 |
+
" ": 50260,
|
37 |
+
" ": 50259,
|
38 |
+
" ": 50258,
|
39 |
+
" ": 50257,
|
40 |
+
"<|im_end|>": 50295,
|
41 |
+
"<|im_start|>": 50296
|
42 |
+
}
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/phi-2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"PhiForCausalLM"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
|
10 |
+
"AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
|
11 |
+
},
|
12 |
+
"embd_pdrop": 0.0,
|
13 |
+
"flash_attn": false,
|
14 |
+
"flash_rotary": false,
|
15 |
+
"fused_dense": false,
|
16 |
+
"gradient_checkpointing": false,
|
17 |
+
"img_processor": null,
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"model_type": "phi-msft",
|
21 |
+
"n_embd": 2560,
|
22 |
+
"n_head": 32,
|
23 |
+
"n_head_kv": null,
|
24 |
+
"n_inner": null,
|
25 |
+
"n_layer": 32,
|
26 |
+
"n_positions": 2048,
|
27 |
+
"resid_pdrop": 0.1,
|
28 |
+
"rotary_dim": 32,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"torch_dtype": "bfloat16",
|
31 |
+
"transformers_version": "4.36.2",
|
32 |
+
"use_cache": false,
|
33 |
+
"vocab_size": 51200
|
34 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.36.2"
|
4 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0649a4b7eaf67161f7c9c2f41d1809f0ab639ff54da45ac29c4146fb420c524
|
3 |
+
size 4982468168
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:632f4e8b7ddaca4161b9a960db9d728ca590e0db2ca59ea944995016af57347f
|
3 |
+
size 576934152
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,332 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 5559367680
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.linear.bias": "model-00002-of-00002.safetensors",
|
7 |
+
"lm_head.linear.weight": "model-00002-of-00002.safetensors",
|
8 |
+
"lm_head.ln.bias": "model-00002-of-00002.safetensors",
|
9 |
+
"lm_head.ln.weight": "model-00002-of-00002.safetensors",
|
10 |
+
"transformer.embd.wte.weight": "model-00001-of-00002.safetensors",
|
11 |
+
"transformer.h.0.ln.bias": "model-00001-of-00002.safetensors",
|
12 |
+
"transformer.h.0.ln.weight": "model-00001-of-00002.safetensors",
|
13 |
+
"transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
14 |
+
"transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
15 |
+
"transformer.h.0.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
16 |
+
"transformer.h.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
17 |
+
"transformer.h.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
18 |
+
"transformer.h.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
19 |
+
"transformer.h.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
20 |
+
"transformer.h.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
21 |
+
"transformer.h.1.ln.bias": "model-00001-of-00002.safetensors",
|
22 |
+
"transformer.h.1.ln.weight": "model-00001-of-00002.safetensors",
|
23 |
+
"transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
24 |
+
"transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
25 |
+
"transformer.h.1.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
26 |
+
"transformer.h.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
27 |
+
"transformer.h.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
28 |
+
"transformer.h.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
29 |
+
"transformer.h.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
30 |
+
"transformer.h.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
31 |
+
"transformer.h.10.ln.bias": "model-00001-of-00002.safetensors",
|
32 |
+
"transformer.h.10.ln.weight": "model-00001-of-00002.safetensors",
|
33 |
+
"transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
34 |
+
"transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
35 |
+
"transformer.h.10.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
36 |
+
"transformer.h.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
37 |
+
"transformer.h.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
38 |
+
"transformer.h.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
39 |
+
"transformer.h.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
40 |
+
"transformer.h.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
41 |
+
"transformer.h.11.ln.bias": "model-00001-of-00002.safetensors",
|
42 |
+
"transformer.h.11.ln.weight": "model-00001-of-00002.safetensors",
|
43 |
+
"transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
44 |
+
"transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
45 |
+
"transformer.h.11.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
46 |
+
"transformer.h.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
47 |
+
"transformer.h.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
48 |
+
"transformer.h.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
49 |
+
"transformer.h.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
50 |
+
"transformer.h.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
51 |
+
"transformer.h.12.ln.bias": "model-00001-of-00002.safetensors",
|
52 |
+
"transformer.h.12.ln.weight": "model-00001-of-00002.safetensors",
|
53 |
+
"transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
54 |
+
"transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
55 |
+
"transformer.h.12.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
56 |
+
"transformer.h.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
57 |
+
"transformer.h.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
58 |
+
"transformer.h.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
59 |
+
"transformer.h.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
60 |
+
"transformer.h.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
61 |
+
"transformer.h.13.ln.bias": "model-00001-of-00002.safetensors",
|
62 |
+
"transformer.h.13.ln.weight": "model-00001-of-00002.safetensors",
|
63 |
+
"transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
64 |
+
"transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
65 |
+
"transformer.h.13.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
66 |
+
"transformer.h.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
67 |
+
"transformer.h.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
68 |
+
"transformer.h.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
69 |
+
"transformer.h.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
70 |
+
"transformer.h.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
71 |
+
"transformer.h.14.ln.bias": "model-00001-of-00002.safetensors",
|
72 |
+
"transformer.h.14.ln.weight": "model-00001-of-00002.safetensors",
|
73 |
+
"transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
74 |
+
"transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
75 |
+
"transformer.h.14.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
76 |
+
"transformer.h.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
77 |
+
"transformer.h.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
78 |
+
"transformer.h.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
79 |
+
"transformer.h.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
80 |
+
"transformer.h.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
81 |
+
"transformer.h.15.ln.bias": "model-00001-of-00002.safetensors",
|
82 |
+
"transformer.h.15.ln.weight": "model-00001-of-00002.safetensors",
|
83 |
+
"transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
84 |
+
"transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
85 |
+
"transformer.h.15.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
86 |
+
"transformer.h.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
87 |
+
"transformer.h.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
88 |
+
"transformer.h.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
89 |
+
"transformer.h.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
90 |
+
"transformer.h.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
91 |
+
"transformer.h.16.ln.bias": "model-00001-of-00002.safetensors",
|
92 |
+
"transformer.h.16.ln.weight": "model-00001-of-00002.safetensors",
|
93 |
+
"transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
94 |
+
"transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
95 |
+
"transformer.h.16.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
96 |
+
"transformer.h.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
97 |
+
"transformer.h.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
98 |
+
"transformer.h.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
99 |
+
"transformer.h.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
100 |
+
"transformer.h.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
101 |
+
"transformer.h.17.ln.bias": "model-00001-of-00002.safetensors",
|
102 |
+
"transformer.h.17.ln.weight": "model-00001-of-00002.safetensors",
|
103 |
+
"transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
104 |
+
"transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
105 |
+
"transformer.h.17.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
106 |
+
"transformer.h.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
107 |
+
"transformer.h.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
108 |
+
"transformer.h.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
109 |
+
"transformer.h.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
110 |
+
"transformer.h.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
111 |
+
"transformer.h.18.ln.bias": "model-00001-of-00002.safetensors",
|
112 |
+
"transformer.h.18.ln.weight": "model-00001-of-00002.safetensors",
|
113 |
+
"transformer.h.18.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
114 |
+
"transformer.h.18.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
115 |
+
"transformer.h.18.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
116 |
+
"transformer.h.18.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
117 |
+
"transformer.h.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
118 |
+
"transformer.h.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
119 |
+
"transformer.h.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
120 |
+
"transformer.h.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
121 |
+
"transformer.h.19.ln.bias": "model-00001-of-00002.safetensors",
|
122 |
+
"transformer.h.19.ln.weight": "model-00001-of-00002.safetensors",
|
123 |
+
"transformer.h.19.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
124 |
+
"transformer.h.19.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
125 |
+
"transformer.h.19.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
126 |
+
"transformer.h.19.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
127 |
+
"transformer.h.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
128 |
+
"transformer.h.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
129 |
+
"transformer.h.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
130 |
+
"transformer.h.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
131 |
+
"transformer.h.2.ln.bias": "model-00001-of-00002.safetensors",
|
132 |
+
"transformer.h.2.ln.weight": "model-00001-of-00002.safetensors",
|
133 |
+
"transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
134 |
+
"transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
135 |
+
"transformer.h.2.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
136 |
+
"transformer.h.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
137 |
+
"transformer.h.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
138 |
+
"transformer.h.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
139 |
+
"transformer.h.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
140 |
+
"transformer.h.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
141 |
+
"transformer.h.20.ln.bias": "model-00001-of-00002.safetensors",
|
142 |
+
"transformer.h.20.ln.weight": "model-00001-of-00002.safetensors",
|
143 |
+
"transformer.h.20.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
144 |
+
"transformer.h.20.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
145 |
+
"transformer.h.20.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
146 |
+
"transformer.h.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
147 |
+
"transformer.h.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
148 |
+
"transformer.h.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
149 |
+
"transformer.h.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
150 |
+
"transformer.h.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
151 |
+
"transformer.h.21.ln.bias": "model-00001-of-00002.safetensors",
|
152 |
+
"transformer.h.21.ln.weight": "model-00001-of-00002.safetensors",
|
153 |
+
"transformer.h.21.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
154 |
+
"transformer.h.21.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
155 |
+
"transformer.h.21.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
156 |
+
"transformer.h.21.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
157 |
+
"transformer.h.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
158 |
+
"transformer.h.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
159 |
+
"transformer.h.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
160 |
+
"transformer.h.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
161 |
+
"transformer.h.22.ln.bias": "model-00001-of-00002.safetensors",
|
162 |
+
"transformer.h.22.ln.weight": "model-00001-of-00002.safetensors",
|
163 |
+
"transformer.h.22.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
164 |
+
"transformer.h.22.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
165 |
+
"transformer.h.22.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
166 |
+
"transformer.h.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
167 |
+
"transformer.h.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
168 |
+
"transformer.h.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
169 |
+
"transformer.h.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
170 |
+
"transformer.h.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
171 |
+
"transformer.h.23.ln.bias": "model-00001-of-00002.safetensors",
|
172 |
+
"transformer.h.23.ln.weight": "model-00001-of-00002.safetensors",
|
173 |
+
"transformer.h.23.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
174 |
+
"transformer.h.23.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
175 |
+
"transformer.h.23.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
176 |
+
"transformer.h.23.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
177 |
+
"transformer.h.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
178 |
+
"transformer.h.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
179 |
+
"transformer.h.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
180 |
+
"transformer.h.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
181 |
+
"transformer.h.24.ln.bias": "model-00001-of-00002.safetensors",
|
182 |
+
"transformer.h.24.ln.weight": "model-00001-of-00002.safetensors",
|
183 |
+
"transformer.h.24.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
184 |
+
"transformer.h.24.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
185 |
+
"transformer.h.24.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
186 |
+
"transformer.h.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
187 |
+
"transformer.h.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
188 |
+
"transformer.h.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
189 |
+
"transformer.h.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
190 |
+
"transformer.h.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
191 |
+
"transformer.h.25.ln.bias": "model-00001-of-00002.safetensors",
|
192 |
+
"transformer.h.25.ln.weight": "model-00001-of-00002.safetensors",
|
193 |
+
"transformer.h.25.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
194 |
+
"transformer.h.25.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
195 |
+
"transformer.h.25.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
196 |
+
"transformer.h.25.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
197 |
+
"transformer.h.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
198 |
+
"transformer.h.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
199 |
+
"transformer.h.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
200 |
+
"transformer.h.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
201 |
+
"transformer.h.26.ln.bias": "model-00001-of-00002.safetensors",
|
202 |
+
"transformer.h.26.ln.weight": "model-00001-of-00002.safetensors",
|
203 |
+
"transformer.h.26.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
204 |
+
"transformer.h.26.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
205 |
+
"transformer.h.26.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
206 |
+
"transformer.h.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
207 |
+
"transformer.h.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
208 |
+
"transformer.h.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
209 |
+
"transformer.h.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
210 |
+
"transformer.h.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
211 |
+
"transformer.h.27.ln.bias": "model-00001-of-00002.safetensors",
|
212 |
+
"transformer.h.27.ln.weight": "model-00001-of-00002.safetensors",
|
213 |
+
"transformer.h.27.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
214 |
+
"transformer.h.27.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
215 |
+
"transformer.h.27.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
216 |
+
"transformer.h.27.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
217 |
+
"transformer.h.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
218 |
+
"transformer.h.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
219 |
+
"transformer.h.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
220 |
+
"transformer.h.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
221 |
+
"transformer.h.28.ln.bias": "model-00001-of-00002.safetensors",
|
222 |
+
"transformer.h.28.ln.weight": "model-00001-of-00002.safetensors",
|
223 |
+
"transformer.h.28.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
224 |
+
"transformer.h.28.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
225 |
+
"transformer.h.28.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
226 |
+
"transformer.h.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
227 |
+
"transformer.h.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
228 |
+
"transformer.h.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
229 |
+
"transformer.h.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
230 |
+
"transformer.h.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
231 |
+
"transformer.h.29.ln.bias": "model-00001-of-00002.safetensors",
|
232 |
+
"transformer.h.29.ln.weight": "model-00001-of-00002.safetensors",
|
233 |
+
"transformer.h.29.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
234 |
+
"transformer.h.29.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
235 |
+
"transformer.h.29.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
236 |
+
"transformer.h.29.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
237 |
+
"transformer.h.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
238 |
+
"transformer.h.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
239 |
+
"transformer.h.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
240 |
+
"transformer.h.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
241 |
+
"transformer.h.3.ln.bias": "model-00001-of-00002.safetensors",
|
242 |
+
"transformer.h.3.ln.weight": "model-00001-of-00002.safetensors",
|
243 |
+
"transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
244 |
+
"transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
245 |
+
"transformer.h.3.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
246 |
+
"transformer.h.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
247 |
+
"transformer.h.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
248 |
+
"transformer.h.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
249 |
+
"transformer.h.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
250 |
+
"transformer.h.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
251 |
+
"transformer.h.30.ln.bias": "model-00001-of-00002.safetensors",
|
252 |
+
"transformer.h.30.ln.weight": "model-00001-of-00002.safetensors",
|
253 |
+
"transformer.h.30.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
|
254 |
+
"transformer.h.30.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
|
255 |
+
"transformer.h.30.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
|
256 |
+
"transformer.h.30.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
|
257 |
+
"transformer.h.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
258 |
+
"transformer.h.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
259 |
+
"transformer.h.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
260 |
+
"transformer.h.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
261 |
+
"transformer.h.31.ln.bias": "model-00002-of-00002.safetensors",
|
262 |
+
"transformer.h.31.ln.weight": "model-00002-of-00002.safetensors",
|
263 |
+
"transformer.h.31.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
|
264 |
+
"transformer.h.31.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
|
265 |
+
"transformer.h.31.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
|
266 |
+
"transformer.h.31.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
|
267 |
+
"transformer.h.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
268 |
+
"transformer.h.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
269 |
+
"transformer.h.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
270 |
+
"transformer.h.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
271 |
+
"transformer.h.4.ln.bias": "model-00001-of-00002.safetensors",
|
272 |
+
"transformer.h.4.ln.weight": "model-00001-of-00002.safetensors",
|
273 |
+
"transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
274 |
+
"transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
275 |
+
"transformer.h.4.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
276 |
+
"transformer.h.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
277 |
+
"transformer.h.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
278 |
+
"transformer.h.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
279 |
+
"transformer.h.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
280 |
+
"transformer.h.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
281 |
+
"transformer.h.5.ln.bias": "model-00001-of-00002.safetensors",
|
282 |
+
"transformer.h.5.ln.weight": "model-00001-of-00002.safetensors",
|
283 |
+
"transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
284 |
+
"transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
285 |
+
"transformer.h.5.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
286 |
+
"transformer.h.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
287 |
+
"transformer.h.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
288 |
+
"transformer.h.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
289 |
+
"transformer.h.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
290 |
+
"transformer.h.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
291 |
+
"transformer.h.6.ln.bias": "model-00001-of-00002.safetensors",
|
292 |
+
"transformer.h.6.ln.weight": "model-00001-of-00002.safetensors",
|
293 |
+
"transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
294 |
+
"transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
295 |
+
"transformer.h.6.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
296 |
+
"transformer.h.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
297 |
+
"transformer.h.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
298 |
+
"transformer.h.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
299 |
+
"transformer.h.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
300 |
+
"transformer.h.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
301 |
+
"transformer.h.7.ln.bias": "model-00001-of-00002.safetensors",
|
302 |
+
"transformer.h.7.ln.weight": "model-00001-of-00002.safetensors",
|
303 |
+
"transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
304 |
+
"transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
305 |
+
"transformer.h.7.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
306 |
+
"transformer.h.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
307 |
+
"transformer.h.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
308 |
+
"transformer.h.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
309 |
+
"transformer.h.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
310 |
+
"transformer.h.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
311 |
+
"transformer.h.8.ln.bias": "model-00001-of-00002.safetensors",
|
312 |
+
"transformer.h.8.ln.weight": "model-00001-of-00002.safetensors",
|
313 |
+
"transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
314 |
+
"transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
315 |
+
"transformer.h.8.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
316 |
+
"transformer.h.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
317 |
+
"transformer.h.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
318 |
+
"transformer.h.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
319 |
+
"transformer.h.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
320 |
+
"transformer.h.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
321 |
+
"transformer.h.9.ln.bias": "model-00001-of-00002.safetensors",
|
322 |
+
"transformer.h.9.ln.weight": "model-00001-of-00002.safetensors",
|
323 |
+
"transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
324 |
+
"transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
325 |
+
"transformer.h.9.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
326 |
+
"transformer.h.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
327 |
+
"transformer.h.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
328 |
+
"transformer.h.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
329 |
+
"transformer.h.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
330 |
+
"transformer.h.9.mlp.fc2.weight": "model-00001-of-00002.safetensors"
|
331 |
+
}
|
332 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|im_end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,344 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"50256": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"50257": {
|
15 |
+
"content": " ",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": false
|
21 |
+
},
|
22 |
+
"50258": {
|
23 |
+
"content": " ",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"50259": {
|
31 |
+
"content": " ",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": false
|
37 |
+
},
|
38 |
+
"50260": {
|
39 |
+
"content": " ",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
},
|
46 |
+
"50261": {
|
47 |
+
"content": " ",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"50262": {
|
55 |
+
"content": " ",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"50263": {
|
63 |
+
"content": " ",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": true,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": false
|
69 |
+
},
|
70 |
+
"50264": {
|
71 |
+
"content": " ",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": true,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"50265": {
|
79 |
+
"content": " ",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": true,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": false
|
85 |
+
},
|
86 |
+
"50266": {
|
87 |
+
"content": " ",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": true,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"50267": {
|
95 |
+
"content": " ",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"50268": {
|
103 |
+
"content": " ",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": true,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"50269": {
|
111 |
+
"content": " ",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": true,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"50270": {
|
119 |
+
"content": " ",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": true,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"50271": {
|
127 |
+
"content": " ",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": true,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"50272": {
|
135 |
+
"content": " ",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": true,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"50273": {
|
143 |
+
"content": " ",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": true,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"50274": {
|
151 |
+
"content": " ",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": true,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"50275": {
|
159 |
+
"content": " ",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": true,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"50276": {
|
167 |
+
"content": " ",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": true,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"50277": {
|
175 |
+
"content": " ",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": true,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
"50278": {
|
183 |
+
"content": " ",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": true,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": false
|
189 |
+
},
|
190 |
+
"50279": {
|
191 |
+
"content": " ",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": true,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": false
|
197 |
+
},
|
198 |
+
"50280": {
|
199 |
+
"content": " ",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": true,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": false
|
205 |
+
},
|
206 |
+
"50281": {
|
207 |
+
"content": " ",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": true,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": false
|
213 |
+
},
|
214 |
+
"50282": {
|
215 |
+
"content": " ",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": true,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": false
|
221 |
+
},
|
222 |
+
"50283": {
|
223 |
+
"content": " ",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": true,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": false
|
229 |
+
},
|
230 |
+
"50284": {
|
231 |
+
"content": " ",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": true,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": false
|
237 |
+
},
|
238 |
+
"50285": {
|
239 |
+
"content": " ",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": true,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": false
|
245 |
+
},
|
246 |
+
"50286": {
|
247 |
+
"content": " ",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": true,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": false
|
253 |
+
},
|
254 |
+
"50287": {
|
255 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": true,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": false
|
261 |
+
},
|
262 |
+
"50288": {
|
263 |
+
"content": "\t\t\t\t\t\t\t\t",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": true,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": false
|
269 |
+
},
|
270 |
+
"50289": {
|
271 |
+
"content": "\t\t\t\t\t\t\t",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": true,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": false
|
277 |
+
},
|
278 |
+
"50290": {
|
279 |
+
"content": "\t\t\t\t\t\t",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": true,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": false
|
285 |
+
},
|
286 |
+
"50291": {
|
287 |
+
"content": "\t\t\t\t\t",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": true,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": false
|
293 |
+
},
|
294 |
+
"50292": {
|
295 |
+
"content": "\t\t\t\t",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": true,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": false
|
301 |
+
},
|
302 |
+
"50293": {
|
303 |
+
"content": "\t\t\t",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": true,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": false
|
309 |
+
},
|
310 |
+
"50294": {
|
311 |
+
"content": "\t\t",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": true,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": false
|
317 |
+
},
|
318 |
+
"50295": {
|
319 |
+
"content": "<|im_end|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"50296": {
|
327 |
+
"content": "<|im_start|>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
}
|
334 |
+
},
|
335 |
+
"bos_token": "<|endoftext|>",
|
336 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
337 |
+
"clean_up_tokenization_spaces": true,
|
338 |
+
"eos_token": "<|im_end|>",
|
339 |
+
"model_max_length": 2048,
|
340 |
+
"pad_token": "<|endoftext|>",
|
341 |
+
"tokenizer_class": "CodeGenTokenizer",
|
342 |
+
"truncation": true,
|
343 |
+
"unk_token": "<|endoftext|>"
|
344 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|