Masnuy commited on
Commit
d548f34
·
verified ·
1 Parent(s): 3be4063

Upload task output 0284a4f8-2ef9-46a5-9d51-1442b3d750d8

Browse files
added_tokens.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "</tool_call>": 151658,
3
- "<tool_call>": 151657,
4
- "<|box_end|>": 151649,
5
- "<|box_start|>": 151648,
6
- "<|endoftext|>": 151643,
7
- "<|file_sep|>": 151664,
8
- "<|fim_middle|>": 151660,
9
- "<|fim_pad|>": 151662,
10
- "<|fim_prefix|>": 151659,
11
- "<|fim_suffix|>": 151661,
12
- "<|im_end|>": 151645,
13
- "<|im_start|>": 151644,
14
- "<|image_pad|>": 151655,
15
- "<|object_ref_end|>": 151647,
16
- "<|object_ref_start|>": 151646,
17
- "<|quad_end|>": 151651,
18
- "<|quad_start|>": 151650,
19
- "<|repo_name|>": 151663,
20
- "<|video_pad|>": 151656,
21
- "<|vision_end|>": 151653,
22
- "<|vision_pad|>": 151654,
23
- "<|vision_start|>": 151652
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -1,30 +1,31 @@
1
  {
2
  "architectures": [
3
- "Qwen2ForCausalLM"
4
  ],
 
5
  "attention_dropout": 0.0,
6
- "eos_token_id": 151643,
7
- "hidden_act": "silu",
8
- "hidden_size": 1536,
 
 
 
9
  "initializer_range": 0.02,
10
- "intermediate_size": 8960,
11
- "max_position_embeddings": 32768,
12
- "max_window_layers": 28,
13
- "model_type": "qwen2",
14
- "num_attention_heads": 12,
15
- "num_hidden_layers": 28,
16
- "num_key_value_heads": 2,
17
- "pad_token_id": 151654,
18
- "rms_norm_eps": 1e-06,
19
  "rope_scaling": null,
20
- "rope_theta": 1000000.0,
21
- "sliding_window": null,
22
- "tie_word_embeddings": true,
 
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.51.3",
25
- "unsloth_fixed": true,
26
  "use_cache": false,
27
- "use_mrope": false,
28
- "use_sliding_window": false,
29
- "vocab_size": 151936
30
  }
 
1
  {
2
  "architectures": [
3
+ "GPTNeoXForCausalLM"
4
  ],
5
+ "attention_bias": true,
6
  "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 1024,
13
  "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "partial_rotary_factor": 0.25,
 
 
21
  "rope_scaling": null,
22
+ "rope_theta": 10000,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
  "torch_dtype": "bfloat16",
27
  "transformers_version": "4.51.3",
 
28
  "use_cache": false,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
 
31
  }
generation_config.json CHANGED
@@ -1,8 +1,6 @@
1
  {
2
- "bos_token_id": 151643,
3
- "eos_token_id": 151643,
4
- "max_length": 32768,
5
- "max_new_tokens": 2048,
6
- "pad_token_id": 151654,
7
  "transformers_version": "4.51.3"
8
  }
 
1
  {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
 
 
5
  "transformers_version": "4.51.3"
6
  }
loss.txt CHANGED
@@ -1 +1 @@
1
- 180,0.9262552261352539
 
1
+ 100,1.2403614521026611
merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62548338bcfefb38217561a96068d2c2776b7c5a0c47cf6ab85b79dbc4b7789a
3
- size 3087467144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7484c0d285200915e037cf921947293d8738f0c41c4e64a2cd780ae907d9b9fe
3
+ size 810702192
special_tokens_map.json CHANGED
@@ -1,19 +1,11 @@
1
  {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>"
16
- ],
17
  "eos_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
@@ -21,8 +13,9 @@
21
  "rstrip": false,
22
  "single_word": false
23
  },
24
- "pad_token": {
25
- "content": "<|vision_pad|>",
 
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
 
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": "<|endoftext|>",
11
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
- size 11421896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c0d99d84af59e9126913fafe5210822963e9a3065ee43e6833b358b0c2f825
3
+ size 3564303
tokenizer_config.json CHANGED
@@ -1,8 +1,9 @@
1
  {
2
  "add_bos_token": false,
 
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
- "151643": {
6
  "content": "<|endoftext|>",
7
  "lstrip": false,
8
  "normalized": false,
@@ -10,199 +11,205 @@
10
  "single_word": false,
11
  "special": true
12
  },
13
- "151644": {
14
- "content": "<|im_start|>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
- "151645": {
22
- "content": "<|im_end|>",
23
  "lstrip": false,
24
- "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
- "special": true
28
  },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
  "lstrip": false,
32
- "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
- "special": true
36
  },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
  "lstrip": false,
40
- "normalized": false,
41
  "rstrip": false,
42
  "single_word": false,
43
- "special": true
44
  },
45
- "151648": {
46
- "content": "<|box_start|>",
47
  "lstrip": false,
48
- "normalized": false,
49
  "rstrip": false,
50
  "single_word": false,
51
- "special": true
52
  },
53
- "151649": {
54
- "content": "<|box_end|>",
55
  "lstrip": false,
56
- "normalized": false,
57
  "rstrip": false,
58
  "single_word": false,
59
- "special": true
60
  },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
  "lstrip": false,
64
- "normalized": false,
65
  "rstrip": false,
66
  "single_word": false,
67
- "special": true
68
  },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
  "lstrip": false,
72
- "normalized": false,
73
  "rstrip": false,
74
  "single_word": false,
75
- "special": true
76
  },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
  "lstrip": false,
80
- "normalized": false,
81
  "rstrip": false,
82
  "single_word": false,
83
- "special": true
84
  },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
  "lstrip": false,
88
- "normalized": false,
89
  "rstrip": false,
90
  "single_word": false,
91
- "special": true
92
  },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
  "lstrip": false,
96
- "normalized": false,
97
  "rstrip": false,
98
  "single_word": false,
99
- "special": true
100
  },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
  "lstrip": false,
104
- "normalized": false,
105
  "rstrip": false,
106
  "single_word": false,
107
- "special": true
108
  },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
  "lstrip": false,
112
- "normalized": false,
113
  "rstrip": false,
114
  "single_word": false,
115
- "special": true
116
  },
117
- "151657": {
118
- "content": "<tool_call>",
119
  "lstrip": false,
120
- "normalized": false,
121
  "rstrip": false,
122
  "single_word": false,
123
  "special": false
124
  },
125
- "151658": {
126
- "content": "</tool_call>",
127
  "lstrip": false,
128
- "normalized": false,
129
  "rstrip": false,
130
  "single_word": false,
131
  "special": false
132
  },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
  "lstrip": false,
136
- "normalized": false,
137
  "rstrip": false,
138
  "single_word": false,
139
  "special": false
140
  },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
  "lstrip": false,
144
- "normalized": false,
145
  "rstrip": false,
146
  "single_word": false,
147
  "special": false
148
  },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
  "lstrip": false,
152
- "normalized": false,
153
  "rstrip": false,
154
  "single_word": false,
155
  "special": false
156
  },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
  "lstrip": false,
160
- "normalized": false,
161
  "rstrip": false,
162
  "single_word": false,
163
  "special": false
164
  },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
  "lstrip": false,
168
- "normalized": false,
169
  "rstrip": false,
170
  "single_word": false,
171
  "special": false
172
  },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
  "lstrip": false,
176
- "normalized": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
177
  "rstrip": false,
178
  "single_word": false,
179
  "special": false
180
  }
181
  },
182
- "additional_special_tokens": [
183
- "<|im_start|>",
184
- "<|im_end|>",
185
- "<|object_ref_start|>",
186
- "<|object_ref_end|>",
187
- "<|box_start|>",
188
- "<|box_end|>",
189
- "<|quad_start|>",
190
- "<|quad_end|>",
191
- "<|vision_start|>",
192
- "<|vision_end|>",
193
- "<|vision_pad|>",
194
- "<|image_pad|>",
195
- "<|video_pad|>"
196
- ],
197
- "bos_token": null,
198
  "clean_up_tokenization_spaces": false,
199
  "eos_token": "<|endoftext|>",
200
- "errors": "replace",
201
  "extra_special_tokens": {},
202
- "model_max_length": 32768,
203
- "pad_token": "<|vision_pad|>",
204
- "padding_side": "left",
205
- "split_special_tokens": false,
206
- "tokenizer_class": "Qwen2Tokenizer",
207
- "unk_token": null
208
  }
 
1
  {
2
  "add_bos_token": false,
3
+ "add_eos_token": false,
4
  "add_prefix_space": false,
5
  "added_tokens_decoder": {
6
+ "0": {
7
  "content": "<|endoftext|>",
8
  "lstrip": false,
9
  "normalized": false,
 
11
  "single_word": false,
12
  "special": true
13
  },
14
+ "1": {
15
+ "content": "<|padding|>",
16
  "lstrip": false,
17
  "normalized": false,
18
  "rstrip": false,
19
  "single_word": false,
20
  "special": true
21
  },
22
+ "50254": {
23
+ "content": " ",
24
  "lstrip": false,
25
+ "normalized": true,
26
  "rstrip": false,
27
  "single_word": false,
28
+ "special": false
29
  },
30
+ "50255": {
31
+ "content": " ",
32
  "lstrip": false,
33
+ "normalized": true,
34
  "rstrip": false,
35
  "single_word": false,
36
+ "special": false
37
  },
38
+ "50256": {
39
+ "content": " ",
40
  "lstrip": false,
41
+ "normalized": true,
42
  "rstrip": false,
43
  "single_word": false,
44
+ "special": false
45
  },
46
+ "50257": {
47
+ "content": " ",
48
  "lstrip": false,
49
+ "normalized": true,
50
  "rstrip": false,
51
  "single_word": false,
52
+ "special": false
53
  },
54
+ "50258": {
55
+ "content": " ",
56
  "lstrip": false,
57
+ "normalized": true,
58
  "rstrip": false,
59
  "single_word": false,
60
+ "special": false
61
  },
62
+ "50259": {
63
+ "content": " ",
64
  "lstrip": false,
65
+ "normalized": true,
66
  "rstrip": false,
67
  "single_word": false,
68
+ "special": false
69
  },
70
+ "50260": {
71
+ "content": " ",
72
  "lstrip": false,
73
+ "normalized": true,
74
  "rstrip": false,
75
  "single_word": false,
76
+ "special": false
77
  },
78
+ "50261": {
79
+ "content": " ",
80
  "lstrip": false,
81
+ "normalized": true,
82
  "rstrip": false,
83
  "single_word": false,
84
+ "special": false
85
  },
86
+ "50262": {
87
+ "content": " ",
88
  "lstrip": false,
89
+ "normalized": true,
90
  "rstrip": false,
91
  "single_word": false,
92
+ "special": false
93
  },
94
+ "50263": {
95
+ "content": " ",
96
  "lstrip": false,
97
+ "normalized": true,
98
  "rstrip": false,
99
  "single_word": false,
100
+ "special": false
101
  },
102
+ "50264": {
103
+ "content": " ",
104
  "lstrip": false,
105
+ "normalized": true,
106
  "rstrip": false,
107
  "single_word": false,
108
+ "special": false
109
  },
110
+ "50265": {
111
+ "content": " ",
112
  "lstrip": false,
113
+ "normalized": true,
114
  "rstrip": false,
115
  "single_word": false,
116
+ "special": false
117
  },
118
+ "50266": {
119
+ "content": " ",
120
  "lstrip": false,
121
+ "normalized": true,
122
  "rstrip": false,
123
  "single_word": false,
124
  "special": false
125
  },
126
+ "50267": {
127
+ "content": " ",
128
  "lstrip": false,
129
+ "normalized": true,
130
  "rstrip": false,
131
  "single_word": false,
132
  "special": false
133
  },
134
+ "50268": {
135
+ "content": " ",
136
  "lstrip": false,
137
+ "normalized": true,
138
  "rstrip": false,
139
  "single_word": false,
140
  "special": false
141
  },
142
+ "50269": {
143
+ "content": " ",
144
  "lstrip": false,
145
+ "normalized": true,
146
  "rstrip": false,
147
  "single_word": false,
148
  "special": false
149
  },
150
+ "50270": {
151
+ "content": " ",
152
  "lstrip": false,
153
+ "normalized": true,
154
  "rstrip": false,
155
  "single_word": false,
156
  "special": false
157
  },
158
+ "50271": {
159
+ "content": " ",
160
  "lstrip": false,
161
+ "normalized": true,
162
  "rstrip": false,
163
  "single_word": false,
164
  "special": false
165
  },
166
+ "50272": {
167
+ "content": " ",
168
  "lstrip": false,
169
+ "normalized": true,
170
  "rstrip": false,
171
  "single_word": false,
172
  "special": false
173
  },
174
+ "50273": {
175
+ "content": " ",
176
  "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
  "rstrip": false,
203
  "single_word": false,
204
  "special": false
205
  }
206
  },
207
+ "bos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
208
  "clean_up_tokenization_spaces": false,
209
  "eos_token": "<|endoftext|>",
 
210
  "extra_special_tokens": {},
211
+ "model_max_length": 1000000000000000019884624838656,
212
+ "pad_token": "<|endoftext|>",
213
+ "tokenizer_class": "GPTNeoXTokenizer",
214
+ "unk_token": "<|endoftext|>"
 
 
215
  }
vocab.json DELETED
The diff for this file is too large to render. See raw diff