OwOpeepeepoopoo commited on
Commit
7ea0902
1 Parent(s): 7be09a9

Upload model

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 100289
3
+ }
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/kaggle/working/dippy-bittensor-subnet/dippy_validation_api/output_clone_Aspik101_sn11_mistral_ft_v196_ft1001_train_2e-07_3_25/checkpoint-10",
3
+ "architectures": [
4
+ "StableLmForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 100257,
8
+ "eos_token_id": 100257,
9
+ "hidden_act": "silu",
10
+ "hidden_dropout": 0.0,
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 4096,
16
+ "model_type": "stablelm",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 32,
20
+ "pad_token_id": 100257,
21
+ "partial_rotary_factor": 0.25,
22
+ "qk_layernorm": false,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.41.2",
28
+ "use_cache": false,
29
+ "use_parallel_residual": false,
30
+ "use_qkv_bias": true,
31
+ "vocab_size": 100352
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "do_sample": true,
5
+ "eos_token_id": 100257,
6
+ "transformers_version": "4.41.2"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2642b944fa454e61d9b2a8790e292b68db84a68631057f737c50f0a1628c6fdd
3
+ size 2991153616
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e83b36fd41b4a1d992e6de3ec00d7dfc15f2c4d170f5f15a4af116779a40e18
3
+ size 2764862448
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4086a25994a248867b1385b62b101342bc7ada19e203d8d2e7dd091039d3ab3a
3
+ size 822083712
model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6578061312
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.10.input_layernorm.bias": "model-00002-of-00003.safetensors",
37
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.10.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
42
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
44
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
47
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
48
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
49
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.11.input_layernorm.bias": "model-00002-of-00003.safetensors",
51
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.11.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
56
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
58
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
61
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
63
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
65
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
70
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
72
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
75
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
77
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
79
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
84
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
86
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
89
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
91
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
93
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.14.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
98
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
100
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
103
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
105
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
107
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
112
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
114
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
117
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
119
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
120
+ "model.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
121
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
122
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
123
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
124
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
125
+ "model.layers.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
126
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
128
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
131
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
133
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
135
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
140
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
142
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
145
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
147
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
149
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
154
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
156
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
159
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
161
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
163
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
167
+ "model.layers.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
168
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
169
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
170
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
173
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
174
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
175
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
176
+ "model.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
177
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
178
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
179
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
180
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
181
+ "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
182
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
183
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
184
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
185
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
186
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
187
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
188
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
189
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
190
+ "model.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
191
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
192
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
193
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
194
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
195
+ "model.layers.20.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
196
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
198
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
199
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
201
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
202
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
203
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
204
+ "model.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
205
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
206
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
207
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
208
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
209
+ "model.layers.21.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
210
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
211
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
212
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
213
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
214
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
215
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
216
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
217
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
218
+ "model.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
219
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
220
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
221
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
222
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
223
+ "model.layers.22.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
224
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
225
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
226
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
227
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
228
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
229
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
230
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
231
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
232
+ "model.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
233
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
234
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
235
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
236
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
237
+ "model.layers.23.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
238
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
239
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
240
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
241
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
243
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
244
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
245
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
247
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
252
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
254
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
257
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
259
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
261
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
266
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
268
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
271
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
273
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
275
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
280
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
282
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
285
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
287
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
289
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
294
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
296
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
297
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
298
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
299
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
300
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
301
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
302
+ "model.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
303
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
304
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
305
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
306
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
307
+ "model.layers.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
308
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
309
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
310
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
311
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
312
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
313
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
314
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
315
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
316
+ "model.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
317
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
318
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
319
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
320
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
321
+ "model.layers.8.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
322
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
323
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
324
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
325
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
326
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
327
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
328
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
329
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
330
+ "model.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
331
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
332
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
333
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
334
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
335
+ "model.layers.9.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
344
+ "model.norm.bias": "model-00002-of-00003.safetensors",
345
+ "model.norm.weight": "model-00002-of-00003.safetensors"
346
+ }
347
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|reg_extra|>",
4
+ "<|endoftext|>",
5
+ "<|fim_prefix|>",
6
+ "<|fim_middle|>",
7
+ "<|fim_suffix|>",
8
+ "<|fim_pad|>",
9
+ "<gh_stars>",
10
+ "<filename>",
11
+ "<issue_start>",
12
+ "<issue_comment>",
13
+ "<issue_closed>",
14
+ "<jupyter_start>",
15
+ "<jupyter_text>",
16
+ "<jupyter_code>",
17
+ "<jupyter_output>",
18
+ "<empty_output>",
19
+ "<commit_before>",
20
+ "<commit_msg>",
21
+ "<commit_after>",
22
+ "<reponame>",
23
+ "<|endofprompt|>",
24
+ "<|im_start|>",
25
+ "<|im_end|>",
26
+ "<|pause|>",
27
+ "<|reg0|>",
28
+ "<|reg1|>",
29
+ "<|reg2|>",
30
+ "<|reg3|>",
31
+ "<|reg4|>",
32
+ "<|reg5|>",
33
+ "<|reg6|>",
34
+ "<|reg7|>",
35
+ "<|extra0|>"
36
+ ],
37
+ "bos_token": {
38
+ "content": "<|endoftext|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "eos_token": {
45
+ "content": "<|endoftext|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ },
51
+ "pad_token": {
52
+ "content": "<|endoftext|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false
57
+ },
58
+ "unk_token": {
59
+ "content": "<|endoftext|>",
60
+ "lstrip": false,
61
+ "normalized": false,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,327 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "100256": {
6
+ "content": "<|reg_extra|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "100257": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "100258": {
22
+ "content": "<|fim_prefix|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "100259": {
30
+ "content": "<|fim_middle|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "100260": {
38
+ "content": "<|fim_suffix|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "100261": {
46
+ "content": "<|fim_pad|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "100262": {
54
+ "content": "<gh_stars>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "100263": {
62
+ "content": "<filename>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "100264": {
70
+ "content": "<issue_start>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "100265": {
78
+ "content": "<issue_comment>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "100266": {
86
+ "content": "<issue_closed>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "100267": {
94
+ "content": "<jupyter_start>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "100268": {
102
+ "content": "<jupyter_text>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "100269": {
110
+ "content": "<jupyter_code>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "100270": {
118
+ "content": "<jupyter_output>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "100271": {
126
+ "content": "<empty_output>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "100272": {
134
+ "content": "<commit_before>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "100273": {
142
+ "content": "<commit_msg>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "100274": {
150
+ "content": "<commit_after>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "100275": {
158
+ "content": "<reponame>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "100276": {
166
+ "content": "<|endofprompt|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "100277": {
174
+ "content": "<|im_start|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "100278": {
182
+ "content": "<|im_end|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "100279": {
190
+ "content": "<|pause|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "100280": {
198
+ "content": "<|reg0|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "100281": {
206
+ "content": "<|reg1|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "100282": {
214
+ "content": "<|reg2|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "100283": {
222
+ "content": "<|reg3|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "100284": {
230
+ "content": "<|reg4|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "100285": {
238
+ "content": "<|reg5|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "100286": {
246
+ "content": "<|reg6|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "100287": {
254
+ "content": "<|reg7|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "100288": {
262
+ "content": "<|extra0|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "100289": {
270
+ "content": "[PAD]",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ }
277
+ },
278
+ "additional_special_tokens": [
279
+ "<|reg_extra|>",
280
+ "<|endoftext|>",
281
+ "<|fim_prefix|>",
282
+ "<|fim_middle|>",
283
+ "<|fim_suffix|>",
284
+ "<|fim_pad|>",
285
+ "<gh_stars>",
286
+ "<filename>",
287
+ "<issue_start>",
288
+ "<issue_comment>",
289
+ "<issue_closed>",
290
+ "<jupyter_start>",
291
+ "<jupyter_text>",
292
+ "<jupyter_code>",
293
+ "<jupyter_output>",
294
+ "<empty_output>",
295
+ "<commit_before>",
296
+ "<commit_msg>",
297
+ "<commit_after>",
298
+ "<reponame>",
299
+ "<|endofprompt|>",
300
+ "<|im_start|>",
301
+ "<|im_end|>",
302
+ "<|pause|>",
303
+ "<|reg0|>",
304
+ "<|reg1|>",
305
+ "<|reg2|>",
306
+ "<|reg3|>",
307
+ "<|reg4|>",
308
+ "<|reg5|>",
309
+ "<|reg6|>",
310
+ "<|reg7|>",
311
+ "<|extra0|>"
312
+ ],
313
+ "bos_token": "<|endoftext|>",
314
+ "clean_up_tokenization_spaces": true,
315
+ "eos_token": "<|endoftext|>",
316
+ "max_length": 3896,
317
+ "model_max_length": 1000000000000000019884624838656,
318
+ "pad_to_multiple_of": null,
319
+ "pad_token": "<|endoftext|>",
320
+ "pad_token_type_id": 0,
321
+ "padding_side": "right",
322
+ "stride": 0,
323
+ "tokenizer_class": "GPT2Tokenizer",
324
+ "truncation_side": "right",
325
+ "truncation_strategy": "longest_first",
326
+ "unk_token": "<|endoftext|>"
327
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff