bimabk commited on
Commit
760f605
·
verified ·
1 Parent(s): 6e91b11

Upload task output 1

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 896,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4864,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention"
37
+ ],
38
+ "max_position_embeddings": 32768,
39
+ "max_window_layers": 24,
40
+ "model_type": "qwen2",
41
+ "num_attention_heads": 14,
42
+ "num_hidden_layers": 24,
43
+ "num_key_value_heads": 2,
44
+ "pad_token_id": 151643,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_parameters": {
47
+ "rope_theta": 1000000.0,
48
+ "rope_type": "default"
49
+ },
50
+ "rope_scaling": null,
51
+ "rope_theta": 10000.0,
52
+ "sliding_window": null,
53
+ "tie_word_embeddings": true,
54
+ "transformers_version": "4.57.5",
55
+ "use_cache": false,
56
+ "use_mrope": false,
57
+ "use_sliding_window": false,
58
+ "vocab_size": 151936
59
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token_id": [
3
+ 151643
4
+ ],
5
+ "max_new_tokens": 2048,
6
+ "pad_token_id": 151643,
7
+ "transformers_version": "4.57.5"
8
+ }
loss.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 1,no_eval
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04d65e87191b4d1d641eefc052259fc469c67cb2f0e3db50660efccb05513590
3
+ size 988097824
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": "<|box_end|>",
3
+ "<|box_start|>": "<|box_start|>",
4
+ "<|im_end|>": "<|im_end|>",
5
+ "<|im_start|>": "<|im_start|>",
6
+ "<|image_pad|>": "<|image_pad|>",
7
+ "<|object_ref_end|>": "<|object_ref_end|>",
8
+ "<|object_ref_start|>": "<|object_ref_start|>",
9
+ "<|quad_end|>": "<|quad_end|>",
10
+ "<|quad_start|>": "<|quad_start|>",
11
+ "<|video_pad|>": "<|video_pad|>",
12
+ "<|vision_end|>": "<|vision_end|>",
13
+ "<|vision_pad|>": "<|vision_pad|>",
14
+ "<|vision_start|>": "<|vision_start|>",
15
+ "eos_token": {
16
+ "content": "<|endoftext|>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
3
+ size 11421892
tokenizer_config.json ADDED
@@ -0,0 +1,221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": "<|box_end|>",
3
+ "<|box_start|>": "<|box_start|>",
4
+ "<|im_end|>": "<|im_end|>",
5
+ "<|im_start|>": "<|im_start|>",
6
+ "<|image_pad|>": "<|image_pad|>",
7
+ "<|object_ref_end|>": "<|object_ref_end|>",
8
+ "<|object_ref_start|>": "<|object_ref_start|>",
9
+ "<|quad_end|>": "<|quad_end|>",
10
+ "<|quad_start|>": "<|quad_start|>",
11
+ "<|video_pad|>": "<|video_pad|>",
12
+ "<|vision_end|>": "<|vision_end|>",
13
+ "<|vision_pad|>": "<|vision_pad|>",
14
+ "<|vision_start|>": "<|vision_start|>",
15
+ "add_prefix_space": false,
16
+ "added_tokens_decoder": {
17
+ "151643": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false,
23
+ "special": true
24
+ },
25
+ "151644": {
26
+ "content": "<|im_start|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false,
31
+ "special": true
32
+ },
33
+ "151645": {
34
+ "content": "<|im_end|>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false,
39
+ "special": true
40
+ },
41
+ "151646": {
42
+ "content": "<|object_ref_start|>",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false,
47
+ "special": true
48
+ },
49
+ "151647": {
50
+ "content": "<|object_ref_end|>",
51
+ "lstrip": false,
52
+ "normalized": false,
53
+ "rstrip": false,
54
+ "single_word": false,
55
+ "special": true
56
+ },
57
+ "151648": {
58
+ "content": "<|box_start|>",
59
+ "lstrip": false,
60
+ "normalized": false,
61
+ "rstrip": false,
62
+ "single_word": false,
63
+ "special": true
64
+ },
65
+ "151649": {
66
+ "content": "<|box_end|>",
67
+ "lstrip": false,
68
+ "normalized": false,
69
+ "rstrip": false,
70
+ "single_word": false,
71
+ "special": true
72
+ },
73
+ "151650": {
74
+ "content": "<|quad_start|>",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": false,
78
+ "single_word": false,
79
+ "special": true
80
+ },
81
+ "151651": {
82
+ "content": "<|quad_end|>",
83
+ "lstrip": false,
84
+ "normalized": false,
85
+ "rstrip": false,
86
+ "single_word": false,
87
+ "special": true
88
+ },
89
+ "151652": {
90
+ "content": "<|vision_start|>",
91
+ "lstrip": false,
92
+ "normalized": false,
93
+ "rstrip": false,
94
+ "single_word": false,
95
+ "special": true
96
+ },
97
+ "151653": {
98
+ "content": "<|vision_end|>",
99
+ "lstrip": false,
100
+ "normalized": false,
101
+ "rstrip": false,
102
+ "single_word": false,
103
+ "special": true
104
+ },
105
+ "151654": {
106
+ "content": "<|vision_pad|>",
107
+ "lstrip": false,
108
+ "normalized": false,
109
+ "rstrip": false,
110
+ "single_word": false,
111
+ "special": true
112
+ },
113
+ "151655": {
114
+ "content": "<|image_pad|>",
115
+ "lstrip": false,
116
+ "normalized": false,
117
+ "rstrip": false,
118
+ "single_word": false,
119
+ "special": true
120
+ },
121
+ "151656": {
122
+ "content": "<|video_pad|>",
123
+ "lstrip": false,
124
+ "normalized": false,
125
+ "rstrip": false,
126
+ "single_word": false,
127
+ "special": true
128
+ },
129
+ "151657": {
130
+ "content": "<tool_call>",
131
+ "lstrip": false,
132
+ "normalized": false,
133
+ "rstrip": false,
134
+ "single_word": false,
135
+ "special": false
136
+ },
137
+ "151658": {
138
+ "content": "</tool_call>",
139
+ "lstrip": false,
140
+ "normalized": false,
141
+ "rstrip": false,
142
+ "single_word": false,
143
+ "special": false
144
+ },
145
+ "151659": {
146
+ "content": "<|fim_prefix|>",
147
+ "lstrip": false,
148
+ "normalized": false,
149
+ "rstrip": false,
150
+ "single_word": false,
151
+ "special": false
152
+ },
153
+ "151660": {
154
+ "content": "<|fim_middle|>",
155
+ "lstrip": false,
156
+ "normalized": false,
157
+ "rstrip": false,
158
+ "single_word": false,
159
+ "special": false
160
+ },
161
+ "151661": {
162
+ "content": "<|fim_suffix|>",
163
+ "lstrip": false,
164
+ "normalized": false,
165
+ "rstrip": false,
166
+ "single_word": false,
167
+ "special": false
168
+ },
169
+ "151662": {
170
+ "content": "<|fim_pad|>",
171
+ "lstrip": false,
172
+ "normalized": false,
173
+ "rstrip": false,
174
+ "single_word": false,
175
+ "special": false
176
+ },
177
+ "151663": {
178
+ "content": "<|repo_name|>",
179
+ "lstrip": false,
180
+ "normalized": false,
181
+ "rstrip": false,
182
+ "single_word": false,
183
+ "special": false
184
+ },
185
+ "151664": {
186
+ "content": "<|file_sep|>",
187
+ "lstrip": false,
188
+ "normalized": false,
189
+ "rstrip": false,
190
+ "single_word": false,
191
+ "special": false
192
+ }
193
+ },
194
+ "backend": "tokenizers",
195
+ "bos_token": null,
196
+ "clean_up_tokenization_spaces": false,
197
+ "eos_token": "<|endoftext|>",
198
+ "errors": "replace",
199
+ "extra_special_tokens": {
200
+ "<|box_end|>": "<|box_end|>",
201
+ "<|box_start|>": "<|box_start|>",
202
+ "<|im_end|>": "<|im_end|>",
203
+ "<|im_start|>": "<|im_start|>",
204
+ "<|image_pad|>": "<|image_pad|>",
205
+ "<|object_ref_end|>": "<|object_ref_end|>",
206
+ "<|object_ref_start|>": "<|object_ref_start|>",
207
+ "<|quad_end|>": "<|quad_end|>",
208
+ "<|quad_start|>": "<|quad_start|>",
209
+ "<|video_pad|>": "<|video_pad|>",
210
+ "<|vision_end|>": "<|vision_end|>",
211
+ "<|vision_pad|>": "<|vision_pad|>",
212
+ "<|vision_start|>": "<|vision_start|>"
213
+ },
214
+ "is_local": false,
215
+ "local_files_only": false,
216
+ "model_max_length": 131072,
217
+ "pad_token": "<|endoftext|>",
218
+ "split_special_tokens": false,
219
+ "tokenizer_class": "Qwen2Tokenizer",
220
+ "unk_token": null
221
+ }
trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.0005614823133071309,
6
+ "eval_steps": 500,
7
+ "global_step": 1,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 5,
13
+ "max_steps": 5343,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 3,
16
+ "save_steps": 500,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": true
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 231430519347456.0,
30
+ "train_batch_size": 140,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f71ef55fda8a2bb042cf855c0731a2d650ce311b544b142889842ca9a7b765e
3
+ size 6417
vocab.json ADDED
The diff for this file is too large to render. See raw diff