aybora commited on
Commit
bf7f4ee
·
verified ·
1 Parent(s): 472ed3e

Upload folder using huggingface_hub

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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
3
+ "architectures": [
4
+ "Qwen2VLForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8960,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_vl",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 2,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "mrope_section": [
23
+ 16,
24
+ 24,
25
+ 24
26
+ ],
27
+ "rope_type": "default",
28
+ "type": "default"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": 32768,
32
+ "tie_word_embeddings": true,
33
+ "tokenizer_padding_side": "right",
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.49.0.dev0",
36
+ "use_cache": true,
37
+ "use_sliding_window": false,
38
+ "video_token_id": 151656,
39
+ "vision_config": {
40
+ "hidden_size": 1536,
41
+ "in_chans": 3,
42
+ "model_type": "qwen2_vl",
43
+ "spatial_patch_size": 14,
44
+ "torch_dtype": "bfloat16"
45
+ },
46
+ "vision_end_token_id": 151653,
47
+ "vision_lr": 2e-06,
48
+ "vision_start_token_id": 151652,
49
+ "vision_token_id": 151654,
50
+ "vocab_size": 151936
51
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": "flash_attention_2",
3
+ "bos_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "pad_token_id": 151643,
10
+ "temperature": 0.01,
11
+ "top_k": 1,
12
+ "top_p": 0.001,
13
+ "transformers_version": "4.49.0.dev0"
14
+ }
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 sha256:52b742df9e01c8f3156b0221486f138c9ce6bc38cb4b2d16f41f4537f3e9929a
3
+ size 4418050848
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 12845056,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
tokenizer_config.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "extra_special_tokens": {},
138
+ "model_max_length": 32768,
139
+ "pad_token": "<|endoftext|>",
140
+ "padding_side": "right",
141
+ "processor_class": "Qwen2VLProcessor",
142
+ "split_special_tokens": false,
143
+ "tokenizer_class": "Qwen2Tokenizer",
144
+ "unk_token": null
145
+ }
trainer_state.json ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.842105263157895,
5
+ "eval_steps": 500,
6
+ "global_step": 20,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.21052631578947367,
13
+ "grad_norm": 8.293423652648926,
14
+ "learning_rate": 0.0,
15
+ "loss": 1.0907,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.42105263157894735,
20
+ "grad_norm": 8.356363296508789,
21
+ "learning_rate": 1e-05,
22
+ "loss": 1.1208,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.631578947368421,
27
+ "grad_norm": 8.640625953674316,
28
+ "learning_rate": 1e-05,
29
+ "loss": 1.1098,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.8421052631578947,
34
+ "grad_norm": 5.440302848815918,
35
+ "learning_rate": 1e-05,
36
+ "loss": 0.9925,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 1.2105263157894737,
41
+ "grad_norm": 6.2790846824646,
42
+ "learning_rate": 1e-05,
43
+ "loss": 1.1493,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 1.4210526315789473,
48
+ "grad_norm": 6.609096050262451,
49
+ "learning_rate": 1e-05,
50
+ "loss": 0.8753,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 1.631578947368421,
55
+ "grad_norm": 12.102945327758789,
56
+ "learning_rate": 1e-05,
57
+ "loss": 0.9279,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 1.8421052631578947,
62
+ "grad_norm": 7.788964748382568,
63
+ "learning_rate": 1e-05,
64
+ "loss": 0.8725,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 2.2105263157894735,
69
+ "grad_norm": 11.209437370300293,
70
+ "learning_rate": 1e-05,
71
+ "loss": 0.9817,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 2.4210526315789473,
76
+ "grad_norm": 6.773443222045898,
77
+ "learning_rate": 1e-05,
78
+ "loss": 0.8019,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 2.6315789473684212,
83
+ "grad_norm": 6.824408054351807,
84
+ "learning_rate": 1e-05,
85
+ "loss": 0.7652,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 2.8421052631578947,
90
+ "grad_norm": 6.099692344665527,
91
+ "learning_rate": 1e-05,
92
+ "loss": 0.7196,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 3.2105263157894735,
97
+ "grad_norm": 9.494585990905762,
98
+ "learning_rate": 1e-05,
99
+ "loss": 0.8614,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 3.4210526315789473,
104
+ "grad_norm": 5.957844257354736,
105
+ "learning_rate": 1e-05,
106
+ "loss": 0.6315,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 3.6315789473684212,
111
+ "grad_norm": 4.620523929595947,
112
+ "learning_rate": 1e-05,
113
+ "loss": 0.6296,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 3.8421052631578947,
118
+ "grad_norm": 4.814481735229492,
119
+ "learning_rate": 1e-05,
120
+ "loss": 0.61,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 4.2105263157894735,
125
+ "grad_norm": 4.219420433044434,
126
+ "learning_rate": 1e-05,
127
+ "loss": 0.7063,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 4.421052631578947,
132
+ "grad_norm": 4.6533026695251465,
133
+ "learning_rate": 1e-05,
134
+ "loss": 0.5283,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 4.631578947368421,
139
+ "grad_norm": 11.828014373779297,
140
+ "learning_rate": 1e-05,
141
+ "loss": 0.4826,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 4.842105263157895,
146
+ "grad_norm": 5.108757972717285,
147
+ "learning_rate": 1e-05,
148
+ "loss": 0.5179,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 4.842105263157895,
153
+ "step": 20,
154
+ "total_flos": 93712012541952.0,
155
+ "train_loss": 0.8187338769435882,
156
+ "train_runtime": 200.6985,
157
+ "train_samples_per_second": 7.499,
158
+ "train_steps_per_second": 0.1
159
+ }
160
+ ],
161
+ "logging_steps": 1.0,
162
+ "max_steps": 20,
163
+ "num_input_tokens_seen": 0,
164
+ "num_train_epochs": 5,
165
+ "save_steps": 200,
166
+ "stateful_callbacks": {
167
+ "TrainerControl": {
168
+ "args": {
169
+ "should_epoch_stop": false,
170
+ "should_evaluate": false,
171
+ "should_log": false,
172
+ "should_save": true,
173
+ "should_training_stop": true
174
+ },
175
+ "attributes": {}
176
+ }
177
+ },
178
+ "total_flos": 93712012541952.0,
179
+ "train_batch_size": 4,
180
+ "trial_name": null,
181
+ "trial_params": null
182
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606501a53b33a13e620eb80a5145a1ba512f74a9c38f59d9a41b4f593f74260d
3
+ size 8376
vocab.json ADDED
The diff for this file is too large to render. See raw diff