Hugging Face's logo

qihoo360
/
RzenEmbed

Safetensors
qwen2_vl
Model card Files
xet
Community
3
binwang777 commited on
Commit
e7e8b04
·
1 Parent(s): c358158

first commit

Browse files
Files changed (24) hide show
  1. .gitattributes +2 -0
  2. README.md +195 -0
  3. added_tokens.json +16 -0
  4. assets/example1.jpg +3 -0
  5. assets/example2.jpg +3 -0
  6. assets/example3.jpg +3 -0
  7. assets/example4.jpg +3 -0
  8. assets/example5.mp4 +3 -0
  9. assets/example6.mp4 +3 -0
  10. chat_template.json +3 -0
  11. config.json +47 -0
  12. generation_config.json +13 -0
  13. merges.txt +0 -0
  14. model-00001-of-00004.safetensors +3 -0
  15. model-00002-of-00004.safetensors +3 -0
  16. model-00003-of-00004.safetensors +3 -0
  17. model-00004-of-00004.safetensors +3 -0
  18. model.safetensors.index.json +737 -0
  19. preprocessor_config.json +19 -0
  20. rzen_embed_inference.py +368 -0
  21. special_tokens_map.json +31 -0
  22. tokenizer.json +0 -0
  23. tokenizer_config.json +143 -0
  24. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ assets/*.mp4 filter=lfs diff=lfs merge=lfs -text
37
+ assets/*.jpg filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # RzenEmbed-v2-7B
2
+
3
+ RzenEmbed-v2-7B is a multimodal embedding model developed and open-sourced by 360CVGroup. It achieves state-of-the-art (SOTA) results on the MMEB-V2, MMEB-Visdoc, and MMEB-Video benchmarks (as of September 29, 2025).
4
+
5
+ ### MMEB-V2
6
+
7
+ | Model | Model Size (B) | Overall | Image-Overall | Video-Overall | Visdoc-Overall |
8
+ | ------------------------ | -------------- | --------- | ------------- | ------------- | -------------- |
9
+ | RzenEmbed-v2-7B | 8.29 | **71.61** | 75.92 | **55.73** | **77.06** |
10
+ | seed-1.6-embedding | unknown | 71.27 | **77.78** | 55.34 | 73.44 |
11
+ | Ops-MM-embedding-v1-7B | 8.29 | 67.61 | 72.72 | 53.76 | 70.34 |
12
+ | Ops-MM-embedding-v1-2B | 2.21 | 63.44 | 69.03 | 47.56 | 66.96 |
13
+ | interestFM-UIR-CAFe-7B | 8.03 | 60.63 | 67.56 | 42.4 | 63.92 |
14
+ | VLM2Vec-V2.0-Qwen2VL-2B | 2.21 | 58.02 | 64.85 | 34.85 | 65.36 |
15
+ | gme-Qwen2-VL-7B-Instruct | 8.29 | 57.83 | 55.95 | 38.43 | 75.18 |
16
+ | gme-Qwen2-VL-2B-Instruct | 2.21 | 54.08 | 51.89 | 33.64 | 72.71 |
17
+
18
+ ### MMEB-Image
19
+
20
+ | Models | Model Size(B) | Image-Overall | I-CLS | I-QA | I-RET | I-VG |
21
+ | ---------------------- | ------------- | ------------- | --------- | --------- | -------- | -------- |
22
+ | seed-1.6-embedding | unknown | **77.78** | **76.06** | **73.97** | 77.9 | 91.25 |
23
+ | RzenEmbed-v2-7B | 8.29 | 75.92 | 70.61 | 71.67 | **78.5** | **92.1** |
24
+ | QQMM-embed-v2 | 8.29 | 75.28 | 72.97 | 71.85 | 76.01 | 87.42 |
25
+ | ReCo-7B | 8.29 | 73.87 | 70.95 | 71.52 | 73.66 | 87.70 |
26
+ | OEmbedding-v1-7B | 8.29 | 72.79 | 70.05 | 68.1 | 73.84 | 88.25 |
27
+ | Ops-MM-embedding-v1-7B | 8.29 | 72.72 | 69.65 | 69.58 | 73.09 | 87.15 |
28
+ | QQMM-embed | 8.29 | 72.18 | 70.07 | 69.52 | 71.18 | 87.08 |
29
+ | B3_Qwen2_7B | 8.29 | 72.00 | 70.00 | 66.50 | 74.10 | 84.60 |
30
+
31
+ ### MMEB-Video
32
+
33
+ | Models | Model Size(B) | Video-Overall | V-CLS | V-QA | V-RET | V-MRET |
34
+ | ------------------------ | ------------- | ------------- | --------- | -------- | --------- | --------- |
35
+ | RzenEmbed-v2-7B | 8.29 | **55.73** | 58.82 | **63.5** | 50.97 | 45.54 |
36
+ | seed-1.6-embedding | unknown | 55.34 | 54.99 | 60.85 | **51.33** | **53.45** |
37
+ | Ops-MM-embedding-v1-7B | 8.29 | 53.76 | **59.68** | 62.22 | 45.72 | 43.21 |
38
+ | interestFM-UIR-CAFe-7B | 8.03 | 42.40 | 35.81 | 58.66 | 34.44 | 39.53 |
39
+ | gme-Qwen2-VL-7B-Instruct | 8.29 | 38.43 | 37.44 | 50.35 | 28.37 | 36.96 |
40
+ | interestFM-UIR-CAFe-0.5B | 0.89 | 35.87 | 33.90 | 41.72 | 29.69 | 39.69 |
41
+ | LamRA-Ret | 8.29 | 34.96 | 39.27 | 42.6 | 24.26 | 32.84 |
42
+ | VLM2Vec-V2.0-Qwen2VL-2B | 2.21 | 34.58 | 39.30 | 34.32 | 28.77 | 36.82 |
43
+
44
+ ### MMEB-Visdoc
45
+
46
+ | Models | Model Size(B) | Visdoc-Overall | ViDoRe-V1 | ViDoRe-V2 | VisRAG | VisDoc-OOD |
47
+ | ------------------------ | ------------- | -------------- | --------- | --------- | -------- | ---------- |
48
+ | RzenEmbed-v2-7B | 8.29 | **77.06** | **89.7** | **60.7** | **88.7** | 44.38 |
49
+ | gme-Qwen2-VL-7B-Instruct | 8.29 | 75.18 | 89.44 | 55.61 | 84.99 | **44.4** |
50
+ | seed-1.6-embedding | unknown | 73.44 | 85.53 | 56.57 | 84.74 | 43.14 |
51
+ | gme-Qwen2-VL-2B-Instruct | 2.21 | 72.71 | 86.15 | 53.96 | 82.52 | 43.12 |
52
+ | colpali-v1.3 | 2.92 | 70.97 | 83.60 | 51.98 | 81.13 | 43.12 |
53
+ | Ops-MM-embedding-v1-7B | 8.29 | 70.34 | 80.05 | 59.59 | 79.32 | 43.34 |
54
+ | Ops-MM-embedding-v1-2B | 2.21 | 66.96 | 76.39 | 53.18 | 77.64 | 41.17 |
55
+ | VLM2Vec-V2.0-Qwen2VL-2B | 2.21 | 65.36 | 75.52 | 44.86 | 79.38 | 39.43 |
56
+
57
+ ## Usage
58
+
59
+ ### Text-to-Image Retrieval
60
+
61
+ Retrieve images that match text captions.
62
+
63
+ ```python
64
+ from rzen_embed_inference import RzenEmbed
65
+
66
+ rzen = RzenEmbed("RzenAI/RzenEmbed-v2-7B")
67
+
68
+ queries = [
69
+ "A curious kitten and a gentle puppy share a moment of connection on the grass.",
70
+ "Fresh fridge full of berries yogurt milk and snacks."
71
+ ]
72
+ candidates = [
73
+ "assets/example1.jpg",
74
+ "assets/example2.jpg",
75
+ ]
76
+
77
+ query_instruction = "Find me an everyday image that matches the given caption: "
78
+ candidate_instruction = "Represent the given image."
79
+
80
+ # Generate embeddings and compute similarity
81
+ query_embeds = rzen.get_fused_embeddings(instruction=query_instruction, texts=queries)
82
+ candidate_embeds = rzen.get_fused_embeddings(instruction=candidate_instruction, images=candidates)
83
+
84
+ # Calculate text-to-image similarity scores
85
+ similarity_scores = query_embeds @ candidate_embeds.T
86
+ print(similarity_scores)
87
+ ```
88
+
89
+ ### Image-to-Text Retrieval
90
+
91
+ Find text captions that best match given images.
92
+
93
+ ```python
94
+ from rzen_embed_inference import RzenEmbed
95
+
96
+ rzen = RzenEmbed("RzenAI/RzenEmbed-v2-7B")
97
+
98
+ queries = [
99
+ "assets/example1.jpg",
100
+ "assets/example2.jpg",
101
+ ]
102
+ candidates = [
103
+ "A curious kitten and a gentle puppy share a moment of connection on the grass.",
104
+ "Fresh fridge full of berries yogurt milk and snacks."
105
+ ]
106
+
107
+ query_instruction = "Find an image caption describing the given everyday image."
108
+
109
+ query_embeds = rzen.get_fused_embeddings(instruction=query_instruction, images=queries)
110
+ candidate_embeds = rzen.get_fused_embeddings(texts=candidates)
111
+
112
+ # Calculate image-to-text similarity scores
113
+ similarity_scores = query_embeds @ candidate_embeds.T
114
+ print(similarity_scores)
115
+ ```
116
+
117
+ ### Document Retrieval
118
+
119
+ Match text queries with document images for information retrieval.
120
+
121
+ ```python
122
+ from rzen_embed_inference import RzenEmbed
123
+
124
+ rzen = RzenEmbed("RzenAI/RzenEmbed-v2-7B")
125
+
126
+ queries = [
127
+ "What is the main variable being analyzed on the x-axis of these graphs?",
128
+ "What is the personnel costs in the 4th year?"
129
+ ]
130
+ candidates = [
131
+ "assets/example3.jpg",
132
+ "assets/example4.jpg",
133
+ ]
134
+
135
+ query_instruction = "Find a document image that matches the given query: "
136
+ candidate_instruction = "Understand the content of the provided document image."
137
+
138
+ # Generate embeddings for document retrieval
139
+ query_embeds = rzen.get_fused_embeddings(instruction=query_instruction, texts=queries)
140
+ candidate_embeds = rzen.get_fused_embeddings(instruction=candidate_instruction, images=candidates)
141
+
142
+ # Calculate text-to-document similarity
143
+ similarity_scores = query_embeds @ candidate_embeds.T
144
+ print(similarity_scores)
145
+ ```
146
+
147
+ ### Video Retrieval
148
+
149
+ Retrieve videos based on text captions.
150
+
151
+ ```python
152
+ import cv2
153
+ import numpy as np
154
+ from rzen_embed_inference import RzenEmbed
155
+
156
+ def extract_frames(video_path, num_frames):
157
+ cap = cv2.VideoCapture(video_path)
158
+ total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
159
+ frame_indices = np.linspace(0, total_frames - 1, num_frames, dtype=int)
160
+ frames = []
161
+ for idx in frame_indices:
162
+ cap.set(cv2.CAP_PROP_POS_FRAMES, idx)
163
+ ret, frame = cap.read()
164
+ if ret:
165
+ frames.append(Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)))
166
+ else:
167
+ break
168
+ cap.release()
169
+ return frames
170
+
171
+ rzen = RzenEmbed("RzenAI/RzenEmbed-v2-7B")
172
+
173
+ queries = [
174
+ "A traditional boat glides along a river lined with blooming cherry blossoms under an overcast sky in a modern cityscape.",
175
+ "Tiny ginger kitten meows cutely by the water."
176
+ ]
177
+
178
+ # Extract frames from videos
179
+ video_path_list = [
180
+ "assets/example5.mp4",
181
+ "assets/example6.mp4",
182
+ ]
183
+ candidates = [extract_frames(video_path, num_frames=8) for video_path in video_path_list]
184
+
185
+ query_instruction = "Find the video snippet that corresponds to the given caption: "
186
+ candidate_instruction = "Understand the content of the provided video."
187
+
188
+ # Generate embeddings for video retrieval
189
+ query_embeds = rzen.get_fused_embeddings(instruction=query_instruction, texts=queries)
190
+ candidate_embeds = rzen.get_fused_embeddings(instruction=candidate_instruction, images=candidates)
191
+
192
+ # Calculate text-to-video similarity scores
193
+ similarity_scores = query_embeds @ candidate_embeds.T
194
+ print(similarity_scores)
195
+ ```
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
+ }
assets/example1.jpg ADDED

Git LFS Details

  • SHA256: 52d2be6748264d763776726aaf6feeb75c4820386fb97462b376b287ac51fbc9
  • Pointer size: 130 Bytes
  • Size of remote file: 56.7 kB
assets/example2.jpg ADDED

Git LFS Details

  • SHA256: ae7fac69157de6688e6559ceeeb851458e83323ef1172ecfb0885ad129c06cab
  • Pointer size: 131 Bytes
  • Size of remote file: 137 kB
assets/example3.jpg ADDED

Git LFS Details

  • SHA256: 4b5a0592d8d876959e84689aedf67145c25bb2ca70ad29e2a26b1d375a7e9114
  • Pointer size: 131 Bytes
  • Size of remote file: 270 kB
assets/example4.jpg ADDED

Git LFS Details

  • SHA256: f2ad96188d0f1cce3dc654ce2af87eb2835a148224dd9d05c3dfa3bccc3f1194
  • Pointer size: 131 Bytes
  • Size of remote file: 432 kB
assets/example5.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aec37ed023b9283233d6ba921085fee1165e4820273c3aaff72eb3cf65f9f08
3
+ size 826260
assets/example6.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1e5ae40d4cfd46c5092d3a0afe24b8bedd921ff3f3bd6deea8de28230e4f471
3
+ size 362746
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "RzenAI/RzenEmbed-v2-7B",
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": 3584,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_vl",
17
+ "num_attention_heads": 28,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 4,
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": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.46.3",
35
+ "use_cache": false,
36
+ "use_sliding_window": false,
37
+ "video_token_id": 151656,
38
+ "vision_config": {
39
+ "in_chans": 3,
40
+ "model_type": "qwen2_vl",
41
+ "spatial_patch_size": 14
42
+ },
43
+ "vision_end_token_id": 151653,
44
+ "vision_start_token_id": 151652,
45
+ "vision_token_id": 151654,
46
+ "vocab_size": 152064
47
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "temperature": 0.01,
10
+ "top_k": 1,
11
+ "top_p": 0.001,
12
+ "transformers_version": "4.46.3"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c807e0ae85b413eabc70116bd0ed2c536912c31ac2d872b0f2449d80cb74f9e
3
+ size 4966659944
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3246ac27306a51544b2749bf6001dc1c22ba8c72da5dfd5b03ab304cfc2ab2b
3
+ size 4991495816
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bea1cfe933351a4d04aa6493639393914d1ace1f3d465329f0126970cf9d24b
3
+ size 4932751040
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d10814adc8a39a53c2cdd4400c035fe1b11d1c0715fdab4bf928266e17e41f
3
+ size 1691924384
model.safetensors.index.json ADDED
@@ -0,0 +1,737 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16582751232
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00004-of-00004.safetensors",
345
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
346
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
347
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
348
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
349
+ "visual.blocks.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
350
+ "visual.blocks.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
351
+ "visual.blocks.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
352
+ "visual.blocks.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
353
+ "visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
354
+ "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
355
+ "visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
356
+ "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
357
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
358
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
359
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
360
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
361
+ "visual.blocks.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
362
+ "visual.blocks.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
363
+ "visual.blocks.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
364
+ "visual.blocks.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
365
+ "visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
366
+ "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
367
+ "visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
368
+ "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
369
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
370
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
371
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
372
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
373
+ "visual.blocks.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
374
+ "visual.blocks.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
375
+ "visual.blocks.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
376
+ "visual.blocks.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
377
+ "visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
378
+ "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
379
+ "visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
380
+ "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
381
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
382
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
383
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
384
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
385
+ "visual.blocks.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
386
+ "visual.blocks.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
387
+ "visual.blocks.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
388
+ "visual.blocks.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
389
+ "visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
390
+ "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
391
+ "visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
392
+ "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
393
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
394
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
395
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
396
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
397
+ "visual.blocks.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
398
+ "visual.blocks.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
399
+ "visual.blocks.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
400
+ "visual.blocks.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
401
+ "visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
402
+ "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
403
+ "visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
404
+ "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
405
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
406
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
407
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
408
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
409
+ "visual.blocks.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
410
+ "visual.blocks.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
411
+ "visual.blocks.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
412
+ "visual.blocks.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
413
+ "visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
414
+ "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
415
+ "visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
416
+ "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
417
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
418
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
419
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
420
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
421
+ "visual.blocks.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
422
+ "visual.blocks.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
423
+ "visual.blocks.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
424
+ "visual.blocks.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
425
+ "visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
426
+ "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
427
+ "visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
428
+ "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
429
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
430
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
431
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
432
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
433
+ "visual.blocks.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
434
+ "visual.blocks.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
435
+ "visual.blocks.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
436
+ "visual.blocks.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
437
+ "visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
438
+ "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
439
+ "visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
440
+ "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
441
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
442
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
443
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
444
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
445
+ "visual.blocks.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
446
+ "visual.blocks.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
447
+ "visual.blocks.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
448
+ "visual.blocks.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
449
+ "visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
450
+ "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
451
+ "visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
452
+ "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
453
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
454
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
455
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
456
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
457
+ "visual.blocks.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
458
+ "visual.blocks.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
459
+ "visual.blocks.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
460
+ "visual.blocks.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
461
+ "visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
462
+ "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
463
+ "visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
464
+ "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
465
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
466
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
467
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
468
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
469
+ "visual.blocks.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
470
+ "visual.blocks.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
471
+ "visual.blocks.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
472
+ "visual.blocks.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
473
+ "visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
474
+ "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
475
+ "visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
476
+ "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
477
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
478
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
479
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
480
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
481
+ "visual.blocks.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
482
+ "visual.blocks.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
483
+ "visual.blocks.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
484
+ "visual.blocks.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
485
+ "visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
486
+ "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
487
+ "visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
488
+ "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
489
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
490
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
491
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
492
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
493
+ "visual.blocks.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
494
+ "visual.blocks.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
495
+ "visual.blocks.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
496
+ "visual.blocks.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
497
+ "visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
498
+ "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
499
+ "visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
500
+ "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
501
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
502
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
503
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
504
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
505
+ "visual.blocks.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
506
+ "visual.blocks.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
507
+ "visual.blocks.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
508
+ "visual.blocks.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
509
+ "visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
510
+ "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
511
+ "visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
512
+ "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
513
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
514
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
515
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
516
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
517
+ "visual.blocks.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
518
+ "visual.blocks.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
519
+ "visual.blocks.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
520
+ "visual.blocks.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
521
+ "visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
522
+ "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
523
+ "visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
524
+ "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
525
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
526
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
527
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
528
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
529
+ "visual.blocks.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
530
+ "visual.blocks.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
531
+ "visual.blocks.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
532
+ "visual.blocks.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
533
+ "visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
534
+ "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
535
+ "visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
536
+ "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
537
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
538
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
539
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
540
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
541
+ "visual.blocks.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
542
+ "visual.blocks.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
543
+ "visual.blocks.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
544
+ "visual.blocks.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
545
+ "visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
546
+ "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
547
+ "visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
548
+ "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
549
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
550
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
551
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
552
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
553
+ "visual.blocks.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
554
+ "visual.blocks.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
555
+ "visual.blocks.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
556
+ "visual.blocks.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
557
+ "visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
558
+ "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
559
+ "visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
560
+ "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
561
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
562
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
563
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
564
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
565
+ "visual.blocks.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
566
+ "visual.blocks.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
567
+ "visual.blocks.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
568
+ "visual.blocks.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
569
+ "visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
570
+ "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
571
+ "visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
572
+ "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
573
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
574
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
575
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
576
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
577
+ "visual.blocks.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
578
+ "visual.blocks.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
579
+ "visual.blocks.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
580
+ "visual.blocks.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
581
+ "visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
582
+ "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
583
+ "visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
584
+ "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
585
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
586
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
587
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
588
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
589
+ "visual.blocks.27.mlp.fc1.bias": "model-00001-of-00004.safetensors",
590
+ "visual.blocks.27.mlp.fc1.weight": "model-00001-of-00004.safetensors",
591
+ "visual.blocks.27.mlp.fc2.bias": "model-00001-of-00004.safetensors",
592
+ "visual.blocks.27.mlp.fc2.weight": "model-00001-of-00004.safetensors",
593
+ "visual.blocks.27.norm1.bias": "model-00001-of-00004.safetensors",
594
+ "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
595
+ "visual.blocks.27.norm2.bias": "model-00001-of-00004.safetensors",
596
+ "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
597
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
598
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
599
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
600
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
601
+ "visual.blocks.28.mlp.fc1.bias": "model-00001-of-00004.safetensors",
602
+ "visual.blocks.28.mlp.fc1.weight": "model-00001-of-00004.safetensors",
603
+ "visual.blocks.28.mlp.fc2.bias": "model-00001-of-00004.safetensors",
604
+ "visual.blocks.28.mlp.fc2.weight": "model-00001-of-00004.safetensors",
605
+ "visual.blocks.28.norm1.bias": "model-00001-of-00004.safetensors",
606
+ "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
607
+ "visual.blocks.28.norm2.bias": "model-00001-of-00004.safetensors",
608
+ "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
609
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
610
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
611
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
612
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
613
+ "visual.blocks.29.mlp.fc1.bias": "model-00001-of-00004.safetensors",
614
+ "visual.blocks.29.mlp.fc1.weight": "model-00001-of-00004.safetensors",
615
+ "visual.blocks.29.mlp.fc2.bias": "model-00001-of-00004.safetensors",
616
+ "visual.blocks.29.mlp.fc2.weight": "model-00001-of-00004.safetensors",
617
+ "visual.blocks.29.norm1.bias": "model-00001-of-00004.safetensors",
618
+ "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
619
+ "visual.blocks.29.norm2.bias": "model-00001-of-00004.safetensors",
620
+ "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
621
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
622
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
623
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
624
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
625
+ "visual.blocks.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
626
+ "visual.blocks.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
627
+ "visual.blocks.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
628
+ "visual.blocks.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
629
+ "visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
630
+ "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
631
+ "visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
632
+ "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
633
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
634
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
635
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
636
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
637
+ "visual.blocks.30.mlp.fc1.bias": "model-00001-of-00004.safetensors",
638
+ "visual.blocks.30.mlp.fc1.weight": "model-00001-of-00004.safetensors",
639
+ "visual.blocks.30.mlp.fc2.bias": "model-00001-of-00004.safetensors",
640
+ "visual.blocks.30.mlp.fc2.weight": "model-00001-of-00004.safetensors",
641
+ "visual.blocks.30.norm1.bias": "model-00001-of-00004.safetensors",
642
+ "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
643
+ "visual.blocks.30.norm2.bias": "model-00001-of-00004.safetensors",
644
+ "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
645
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
646
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
647
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
648
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
649
+ "visual.blocks.31.mlp.fc1.bias": "model-00001-of-00004.safetensors",
650
+ "visual.blocks.31.mlp.fc1.weight": "model-00001-of-00004.safetensors",
651
+ "visual.blocks.31.mlp.fc2.bias": "model-00001-of-00004.safetensors",
652
+ "visual.blocks.31.mlp.fc2.weight": "model-00001-of-00004.safetensors",
653
+ "visual.blocks.31.norm1.bias": "model-00001-of-00004.safetensors",
654
+ "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
655
+ "visual.blocks.31.norm2.bias": "model-00001-of-00004.safetensors",
656
+ "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
657
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
658
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
659
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
660
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
661
+ "visual.blocks.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
662
+ "visual.blocks.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
663
+ "visual.blocks.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
664
+ "visual.blocks.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
665
+ "visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
666
+ "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
667
+ "visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
668
+ "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
669
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
670
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
671
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
672
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
673
+ "visual.blocks.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
674
+ "visual.blocks.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
675
+ "visual.blocks.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
676
+ "visual.blocks.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
677
+ "visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
678
+ "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
679
+ "visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
680
+ "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
681
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
682
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
683
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
684
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
685
+ "visual.blocks.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
686
+ "visual.blocks.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
687
+ "visual.blocks.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
688
+ "visual.blocks.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
689
+ "visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
690
+ "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
691
+ "visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
692
+ "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
693
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
694
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
695
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
696
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
697
+ "visual.blocks.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
698
+ "visual.blocks.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
699
+ "visual.blocks.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
700
+ "visual.blocks.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
701
+ "visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
702
+ "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
703
+ "visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
704
+ "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
705
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
706
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
707
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
708
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
709
+ "visual.blocks.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
710
+ "visual.blocks.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
711
+ "visual.blocks.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
712
+ "visual.blocks.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
713
+ "visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
714
+ "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
715
+ "visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
716
+ "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
717
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
718
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
719
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
720
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
721
+ "visual.blocks.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
722
+ "visual.blocks.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
723
+ "visual.blocks.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
724
+ "visual.blocks.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
725
+ "visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
726
+ "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
727
+ "visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
728
+ "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
729
+ "visual.merger.ln_q.bias": "model-00001-of-00004.safetensors",
730
+ "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
731
+ "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
732
+ "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
733
+ "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
734
+ "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
735
+ "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
736
+ }
737
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "min_pixels": 3136,
3
+ "max_pixels": 12845056,
4
+ "patch_size": 14,
5
+ "temporal_patch_size": 2,
6
+ "merge_size": 2,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessor",
18
+ "processor_class": "Qwen2VLProcessor"
19
+ }
rzen_embed_inference.py ADDED
@@ -0,0 +1,368 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from __future__ import annotations
2
+ from torch import nn
3
+ import logging
4
+ import math
5
+ import os
6
+ from typing import Dict, List, Optional
7
+
8
+ import torch
9
+ from PIL import Image
10
+ from torch.utils.data import DataLoader
11
+ from tqdm.autonotebook import tqdm
12
+ from transformers import AutoModelForVision2Seq, AutoProcessor, AutoConfig
13
+
14
+ from transformers.models.qwen2_vl import Qwen2VLForConditionalGeneration
15
+
16
+
17
+ class RzenEmbed(nn.Module):
18
+ def __init__(
19
+ self,
20
+ model_name: str = "RzenAI/RzenEmbed-v2-7B",
21
+ model_path: Optional[str] = None,
22
+ device: str = "cuda" if torch.cuda.is_available() else "cpu",
23
+ min_image_tokens=256,
24
+ max_image_tokens=1280,
25
+ min_video_tokens=160,
26
+ max_video_tokens=180,
27
+ max_length=2000,
28
+ attn_implementation="flash_attention_2",
29
+ processor: Optional[AutoProcessor] = None,
30
+ **kwargs,
31
+ ) -> None:
32
+ super().__init__()
33
+ model_name = model_path or model_name
34
+
35
+ config = AutoConfig.from_pretrained(model_name, trust_remote_code=True)
36
+ config._attn_implementation = attn_implementation
37
+ config.padding_side = "right"
38
+ config.use_cache = False
39
+
40
+ self.base = Qwen2VLForConditionalGeneration.from_pretrained(
41
+ model_name, config=config,
42
+ torch_dtype=torch.bfloat16, low_cpu_mem_usage=True
43
+ )
44
+
45
+ self.base.eval()
46
+ self.normalize = True
47
+ self.device = device
48
+ self.base = self.base.to(self.device)
49
+ print(f"model.device: {str(self.base.device)}")
50
+ min_pixels = min_image_tokens * 28 * 28
51
+ max_pixels = max_image_tokens * 28 * 28
52
+ self.max_length = max_length
53
+ if processor is None:
54
+ processor = AutoProcessor.from_pretrained(
55
+ model_name, min_pixels=min_pixels, max_pixels=max_pixels
56
+ )
57
+ self.processor = processor
58
+ self.processor.tokenizer.padding_side = 'right'
59
+ self.defualt_instruction = 'You are a helpful assistant.'
60
+ self.sep = ' '
61
+
62
+ min_pixels_video = min_video_tokens * 28 * 28
63
+ max_pixels_video = max_video_tokens * 28 * 28 # debug
64
+ self.qwen2vl_video_processor = AutoProcessor.from_pretrained(
65
+ model_name, min_pixels=min_pixels_video, max_pixels=max_pixels_video
66
+ )
67
+ self.qwen2vl_video_processor.tokenizer.padding_side = 'right'
68
+
69
+ def forward(
70
+ self,
71
+ input_ids: Optional[torch.LongTensor] = None,
72
+ attention_mask: Optional[torch.Tensor] = None,
73
+ position_ids: Optional[torch.LongTensor] = None,
74
+ past_key_values: Optional[List[torch.FloatTensor]] = None,
75
+ inputs_embeds: Optional[torch.FloatTensor] = None,
76
+ pixel_values: Optional[torch.Tensor] = None,
77
+ # pixel_values_videos: Optional[torch.FloatTensor] = None,
78
+ image_grid_thw: Optional[torch.LongTensor] = None,
79
+ # video_grid_thw: Optional[torch.LongTensor] = None,
80
+ pooling_mask: Optional[torch.LongTensor] = None,
81
+ **kwargs
82
+ ) -> torch.Tensor:
83
+ if inputs_embeds is None:
84
+ inputs_embeds = self.base.model.embed_tokens(input_ids)
85
+ has_image = (pixel_values is not None) and any([pv is not None for pv in pixel_values])
86
+ if has_image:
87
+ if type(pixel_values) is list:
88
+ pixel_values = torch.cat([torch.from_numpy(pv) for pv in pixel_values]).to(input_ids.device) # shape=[BS*n_patch,C*H*W]
89
+ image_grid_thw = torch.cat([torch.from_numpy(thw) for thw in image_grid_thw]).to(input_ids.device) # shape=[BS,H,W]
90
+ pixel_values = pixel_values.type(self.base.visual.get_dtype())
91
+ image_embeds = self.base.visual(pixel_values, grid_thw=image_grid_thw).to(inputs_embeds.device)
92
+ image_mask = input_ids == self.base.config.image_token_id
93
+ inputs_embeds[image_mask] = image_embeds
94
+
95
+ if attention_mask is not None:
96
+ attention_mask = attention_mask.to(inputs_embeds.device)
97
+
98
+ # print(inputs_embeds.shape)
99
+ outputs = self.base.model(
100
+ input_ids=None,
101
+ position_ids=position_ids,
102
+ attention_mask=attention_mask,
103
+ past_key_values=past_key_values,
104
+ inputs_embeds=inputs_embeds,
105
+ )
106
+
107
+ pooling_mask = attention_mask if pooling_mask is None else pooling_mask
108
+ left_padding = (pooling_mask[:, -1].sum() == pooling_mask.shape[0]) # TODO
109
+ if left_padding:
110
+ embeddings = outputs.last_hidden_state[:, -1]
111
+ else:
112
+ sequence_lengths = pooling_mask.sum(dim=1) - 1
113
+ batch_size = outputs.last_hidden_state.shape[0]
114
+ embeddings = outputs.last_hidden_state[torch.arange(
115
+ batch_size, device=outputs.last_hidden_state.device
116
+ ), sequence_lengths]
117
+ if self.normalize:
118
+ embeddings = torch.nn.functional.normalize(embeddings, p=2, dim=1)
119
+ return embeddings.contiguous()
120
+
121
+
122
+ def _process_images(self, images):
123
+ """Convert single image or list of images to processed format"""
124
+ if isinstance(images, Image.Image) or isinstance(images, str):
125
+ return [fetch_image(images)]
126
+ return [fetch_image(i) for i in images]
127
+
128
+
129
+ def embed(self, texts: list[str], images: list[Image.Image], **kwargs):
130
+ # self.base.to(self.device)
131
+ # Inputs must be batched
132
+ if any(isinstance(item, list) for item in images):
133
+ is_video = True
134
+ else:
135
+ is_video = False
136
+
137
+ if texts is None and images is None:
138
+ raise ValueError("Either texts or images must be provided")
139
+
140
+ # Determine batch size
141
+
142
+ batch_size = len(texts) if texts is not None else len(images) # type: ignore
143
+
144
+ input_texts, input_images = [], []
145
+ instruction = self.defualt_instruction
146
+ for i in range(batch_size):
147
+ text = texts[i] if texts is not None else None
148
+ image = images[i] if images is not None else None
149
+
150
+ input_str = ""
151
+ processed_image = None
152
+ if image is not None:
153
+ processed_image = self._process_images(image)
154
+ input_images += processed_image
155
+ input_str += "<|vision_start|><|image_pad|><|vision_end|>" * len(processed_image)
156
+
157
+ if text is not None:
158
+ input_str += text
159
+
160
+ msg = f"<|im_start|>system\n{instruction}<|im_end|>\n<|im_start|>user\n{input_str}<|im_end|>\n<|im_start|>assistant\n<|endoftext|>"
161
+
162
+ input_texts.append(msg)
163
+
164
+ if len(input_images) == 0:
165
+ input_images = None
166
+
167
+ if is_video:
168
+ inputs = self.qwen2vl_video_processor(
169
+ text=input_texts,
170
+ images=input_images,
171
+ padding=True,
172
+ truncation=True,
173
+ max_length=self.max_length,
174
+ return_tensors="pt",
175
+ )
176
+ else:
177
+ inputs = self.processor(
178
+ text=input_texts,
179
+ images=input_images,
180
+ padding=True,
181
+ truncation=True,
182
+ max_length=self.max_length,
183
+ return_tensors="pt",
184
+ )
185
+
186
+ inputs = {k: v.to(self.device) for k, v in inputs.items()} # TODO
187
+ with torch.no_grad():
188
+ embeddings = self.forward(**inputs)
189
+ return embeddings
190
+
191
+ def encode(self, sentences: list[str], *, prompt_name=None, **kwargs):
192
+ return self.get_fused_embeddings(texts=sentences, prompt_name=prompt_name, **kwargs)
193
+
194
+ def get_image_embeddings(self, images: list[Image.Image] | DataLoader, **kwargs):
195
+ return self.get_fused_embeddings(images=images, **kwargs)
196
+
197
+ def get_text_embeddings(self, texts: list[str], **kwargs):
198
+ return self.get_fused_embeddings(texts=texts, **kwargs)
199
+
200
+ def get_fused_embeddings(self, texts: list[str] = None, images: list[Image.Image] | DataLoader = None, **kwargs):
201
+ assert texts or images, "Either 'texts' or 'images' must be provided - both cannot be None or empty"
202
+ instruction = kwargs.pop('instruction', None)
203
+ if instruction is not None:
204
+ if texts is not None:
205
+ texts = [instruction + text for text in texts]
206
+ else:
207
+ texts = [instruction] * len(images)
208
+
209
+ if isinstance(images, DataLoader):
210
+ image_loader = images
211
+ batch_size = image_loader.batch_size
212
+ image_loader.dataset.transform = None
213
+ else:
214
+ batch_size = kwargs.pop('batch_size', 32)
215
+ if images is None:
216
+ image_loader = None
217
+ else:
218
+ image_loader = DataLoader(
219
+ images,
220
+ batch_size=batch_size,
221
+ shuffle=False,
222
+ collate_fn=custom_collate_fn,
223
+ num_workers=min(math.floor(os.cpu_count() / 2), 8),
224
+ )
225
+
226
+ if texts is None:
227
+ assert image_loader is not None
228
+ n_batch = len(image_loader)
229
+ else:
230
+ n_batch = len(texts) // batch_size + int(len(texts) % batch_size > 0)
231
+ image_loader = image_loader or [None] * n_batch
232
+
233
+ all_embeddings = list()
234
+ none_batch = [None] * batch_size
235
+ show_progress_bar = kwargs.pop('show_progress_bar', False)
236
+ pbar = tqdm(total=n_batch, disable=not show_progress_bar, mininterval=1, miniters=10, desc='encode')
237
+ for n, img_batch in zip(range(0, n_batch * batch_size, batch_size), image_loader):
238
+ text_batch = none_batch[:len(img_batch)] if texts is None else texts[n: n+batch_size]
239
+ img_batch = none_batch[:len(text_batch)] if img_batch is None else img_batch
240
+ embeddings = self.embed(texts=text_batch, images=img_batch, **kwargs)
241
+ pbar.update(1)
242
+ all_embeddings.append(embeddings.cpu())
243
+ pbar.close()
244
+ all_embeddings = torch.cat(all_embeddings, dim=0)
245
+ return all_embeddings
246
+
247
+
248
+ def custom_collate_fn(batch):
249
+ return batch
250
+
251
+
252
+ ### Copied from qwen_vl_utils.vision_process.py
253
+ import base64
254
+ from io import BytesIO
255
+ import requests
256
+
257
+ IMAGE_FACTOR = 28
258
+ MIN_PIXELS = 4 * 28 * 28
259
+ MAX_PIXELS = 16384 * 28 * 28
260
+ MAX_RATIO = 200
261
+
262
+
263
+ def round_by_factor(number: int, factor: int) -> int:
264
+ """Returns the closest integer to 'number' that is divisible by 'factor'."""
265
+ return round(number / factor) * factor
266
+
267
+
268
+ def ceil_by_factor(number: int, factor: int) -> int:
269
+ """Returns the smallest integer greater than or equal to 'number' that is divisible by 'factor'."""
270
+ return math.ceil(number / factor) * factor
271
+
272
+
273
+ def floor_by_factor(number: int, factor: int) -> int:
274
+ """Returns the largest integer less than or equal to 'number' that is divisible by 'factor'."""
275
+ return math.floor(number / factor) * factor
276
+
277
+
278
+ def smart_resize(
279
+ height: int, width: int, factor: int = IMAGE_FACTOR, min_pixels: int = MIN_PIXELS, max_pixels: int = MAX_PIXELS
280
+ ) -> tuple[int, int]:
281
+ """
282
+ Rescales the image so that the following conditions are met:
283
+
284
+ 1. Both dimensions (height and width) are divisible by 'factor'.
285
+
286
+ 2. The total number of pixels is within the range ['min_pixels', 'max_pixels'].
287
+
288
+ 3. The aspect ratio of the image is maintained as closely as possible.
289
+ """
290
+ h_bar = max(factor, round_by_factor(height, factor))
291
+ w_bar = max(factor, round_by_factor(width, factor))
292
+ if h_bar * w_bar > max_pixels:
293
+ beta = math.sqrt((height * width) / max_pixels)
294
+ h_bar = floor_by_factor(height / beta, factor)
295
+ w_bar = floor_by_factor(width / beta, factor)
296
+ elif h_bar * w_bar < min_pixels:
297
+ beta = math.sqrt(min_pixels / (height * width))
298
+ h_bar = ceil_by_factor(height * beta, factor)
299
+ w_bar = ceil_by_factor(width * beta, factor)
300
+
301
+ if max(h_bar, w_bar) / min(h_bar, w_bar) > MAX_RATIO:
302
+ logging.warning(
303
+ f"Absolute aspect ratio must be smaller than {MAX_RATIO}, got {max(h_bar, w_bar) / min(h_bar, w_bar)}"
304
+ )
305
+ if h_bar > w_bar:
306
+ h_bar = w_bar * MAX_RATIO
307
+ else:
308
+ w_bar = h_bar * MAX_RATIO
309
+ return h_bar, w_bar
310
+
311
+
312
+ def fetch_image(image: str | Image.Image, size_factor: int = IMAGE_FACTOR) -> Image.Image:
313
+ image_obj = None
314
+ if isinstance(image, Image.Image):
315
+ image_obj = image
316
+ elif image.startswith("http://") or image.startswith("https://"):
317
+ headers = {'User-Agent': 'My User Agent 1.0'}
318
+ image_obj = Image.open(requests.get(image, headers=headers, stream=True).raw)
319
+ elif image.startswith("file://"):
320
+ image_obj = Image.open(image[7:])
321
+ elif image.startswith("data:image"):
322
+ if "base64," in image:
323
+ _, base64_data = image.split("base64,", 1)
324
+ data = base64.b64decode(base64_data)
325
+ image_obj = Image.open(BytesIO(data))
326
+ else:
327
+ image_obj = Image.open(image)
328
+ if image_obj is None:
329
+ raise ValueError(f"Unrecognized image input, support local path, http url, base64 and PIL.Image, got {image}")
330
+ image = image_obj.convert("RGB")
331
+
332
+ width, height = image.size
333
+
334
+ resized_height, resized_width = smart_resize(
335
+ height,
336
+ width,
337
+ factor=size_factor,
338
+ min_pixels=MIN_PIXELS,
339
+ max_pixels=MAX_PIXELS,
340
+ )
341
+ image = image.resize((resized_width, resized_height))
342
+
343
+ return image
344
+ ###
345
+
346
+
347
+ if __name__ == '__main__':
348
+ rzen = RzenEmbed("RzenAI/RzenEmbed-v2-7B")
349
+
350
+ queries = [
351
+ "A curious kitten and a gentle puppy share a moment of connection on the grass.",
352
+ "Fresh fridge full of berries yogurt milk and snacks."
353
+ ]
354
+ candidates = [
355
+ "assets/example1.jpg",
356
+ "assets/example2.jpg",
357
+ ]
358
+
359
+ query_instruction = "Find me an everyday image that matches the given caption: "
360
+ candidate_instruction = "Represent the given image."
361
+
362
+ # Generate embeddings and compute similarity
363
+ query_embeds = rzen.get_fused_embeddings(instruction=query_instruction, texts=queries)
364
+ candidate_embeds = rzen.get_fused_embeddings(instruction=candidate_instruction, images=candidates)
365
+
366
+ # Calculate text-to-image similarity scores
367
+ similarity_scores = query_embeds @ candidate_embeds.T
368
+ print(similarity_scores)
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 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "split_special_tokens": false,
141
+ "tokenizer_class": "Qwen2Tokenizer",
142
+ "unk_token": null
143
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff