yujiepan commited on
Commit
cf85772
1 Parent(s): a54a3a3

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ pipeline_tag: text-generation
4
+ inference: true
5
+ widget:
6
+ - text: Hello!
7
+ example_title: Hello world
8
+ group: Python
9
+ ---
10
+
11
+ This model is for debugging. It is randomly initialized using the config from [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct) but with smaller size.
12
+
13
+ Codes:
14
+ ```python
15
+ import os
16
+ from typing import Dict
17
+
18
+ import requests
19
+ import torch
20
+ import transformers
21
+ from PIL import Image
22
+ from torchvision import io
23
+ from transformers import (AutoConfig, AutoModelForCausalLM, AutoProcessor,
24
+ AutoTokenizer, GenerationConfig, pipeline, set_seed)
25
+ from transformers.models.qwen2_vl import Qwen2VLForConditionalGeneration
26
+
27
+ model_id = "Qwen/Qwen2-VL-7B-Instruct"
28
+ repo_id = "yujiepan/qwen2-vl-tiny-random"
29
+ save_path = f"/tmp/{repo_id}"
30
+
31
+ config = AutoConfig.from_pretrained(model_id, trust_remote_code=True)
32
+ config.hidden_size = 16
33
+ config.intermediate_size = 32
34
+ config.num_attention_heads = 2
35
+ config.num_hidden_layers = 2
36
+ config.num_key_value_heads = 1
37
+ config.vision_config.embed_dim = 16
38
+ config.vision_config.num_heads = 2
39
+ config.vision_config.hidden_size = 16
40
+ config.vision_config.depth = 2
41
+ config.rope_scaling['mrope_section'] = [1, 1, 2] # sum needs to be 4 here
42
+
43
+ model = Qwen2VLForConditionalGeneration(config=config)
44
+ model = model.to(torch.bfloat16).cuda().eval()
45
+ model.generation_config = GenerationConfig.from_pretrained(
46
+ model_id, trust_remote_code=True,
47
+ )
48
+ set_seed(42)
49
+ with torch.no_grad():
50
+ for _, p in sorted(model.named_parameters()):
51
+ torch.nn.init.uniform_(p, -0.3, 0.3)
52
+
53
+ processor = AutoProcessor.from_pretrained(model_id)
54
+ model.save_pretrained(save_path)
55
+ processor.save_pretrained(save_path)
56
+ os.system(f"ls -alh {save_path}")
57
+
58
+
59
+ def try_inference():
60
+ url = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"
61
+ image = Image.open(requests.get(url, stream=True).raw)
62
+ conversation = [
63
+ {
64
+ "role": "user",
65
+ "content": [
66
+ {
67
+ "type": "image",
68
+ },
69
+ {"type": "text", "text": "Describe this image."},
70
+ ],
71
+ }
72
+ ]
73
+ processor = AutoProcessor.from_pretrained(save_path)
74
+ model = Qwen2VLForConditionalGeneration.from_pretrained(
75
+ save_path, torch_dtype=torch.bfloat16, device_map='cuda')
76
+ text_prompt = processor.apply_chat_template(
77
+ conversation, add_generation_prompt=True)
78
+ inputs = processor(
79
+ text=[text_prompt], images=[image], padding=True, return_tensors="pt"
80
+ )
81
+ inputs = inputs.to("cuda")
82
+ output_ids = model.generate(**inputs, max_new_tokens=16)
83
+ generated_ids = [
84
+ output_ids[len(input_ids):]
85
+ for input_ids, output_ids in zip(inputs.input_ids, output_ids)
86
+ ]
87
+ output_text = processor.batch_decode(
88
+ generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True
89
+ )
90
+ print(output_text)
91
+
92
+
93
+ try_inference()
94
+ ```
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 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2-VL-7B-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": 16,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 32,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_vl",
17
+ "num_attention_heads": 2,
18
+ "num_hidden_layers": 2,
19
+ "num_key_value_heads": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "mrope_section": [
23
+ 1,
24
+ 1,
25
+ 2
26
+ ],
27
+ "type": "mrope"
28
+ },
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 32768,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.45.0.dev0",
34
+ "use_cache": true,
35
+ "use_sliding_window": false,
36
+ "video_token_id": 151656,
37
+ "vision_config": {
38
+ "depth": 2,
39
+ "embed_dim": 16,
40
+ "hidden_size": 16,
41
+ "in_chans": 3,
42
+ "model_type": "qwen2_vl",
43
+ "num_heads": 2,
44
+ "spatial_patch_size": 14
45
+ },
46
+ "vision_end_token_id": 151653,
47
+ "vision_start_token_id": 151652,
48
+ "vision_token_id": 151654,
49
+ "vocab_size": 152064
50
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.1,
11
+ "top_k": 1,
12
+ "top_p": 0.001,
13
+ "transformers_version": "4.45.0.dev0",
14
+ "trust_remote_code": true
15
+ }
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:e88c7543d8eaefdfe3d5c95aed57887fc7d7ecdcde9af2af89bfb0082c10a610
3
+ size 9808584
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 32768,
138
+ "pad_token": "<|endoftext|>",
139
+ "padding_side": "left",
140
+ "processor_class": "Qwen2VLProcessor",
141
+ "split_special_tokens": false,
142
+ "tokenizer_class": "Qwen2Tokenizer",
143
+ "unk_token": null
144
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff