Image-Text-to-Text
Transformers
ONNX
Safetensors
English
idefics3
conversational
jsulz HF Staff commited on
Commit
05e887d
·
verified ·
1 Parent(s): 7096b23

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,327 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ datasets:
5
+ - HuggingFaceM4/the_cauldron
6
+ - HuggingFaceM4/Docmatix
7
+ pipeline_tag: image-text-to-text
8
+ language:
9
+ - en
10
+ base_model:
11
+ - HuggingFaceTB/SmolLM2-135M-Instruct
12
+ - google/siglip-base-patch16-512
13
+ ---
14
+
15
+ <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/SmolVLM_256_banner.png" width="800" height="auto" alt="Image description">
16
+
17
+ # SmolVLM-256M
18
+
19
+ SmolVLM-256M is the smallest multimodal model in the world. It accepts arbitrary sequences of image and text inputs to produce text outputs. It's designed for efficiency. SmolVLM can answer questions about images, describe visual content, or transcribe text. Its lightweight architecture makes it suitable for on-device applications while maintaining strong performance on multimodal tasks. It can run inference on one image with under 1GB of GPU RAM.
20
+
21
+ ## Model Summary
22
+
23
+ - **Developed by:** Hugging Face 🤗
24
+ - **Model type:** Multi-modal model (image+text)
25
+ - **Language(s) (NLP):** English
26
+ - **License:** Apache 2.0
27
+ - **Architecture:** Based on [Idefics3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) (see technical summary)
28
+
29
+ ## Resources
30
+
31
+ - **Demo:** [SmolVLM-256 Demo](https://huggingface.co/spaces/HuggingFaceTB/SmolVLM-256M-Demo)
32
+ - **Blog:** [Blog post](https://huggingface.co/blog/smolvlm)
33
+
34
+ ## Uses
35
+
36
+ SmolVLM can be used for inference on multimodal (image + text) tasks where the input comprises text queries along with one or more images. Text and images can be interleaved arbitrarily, enabling tasks like image captioning, visual question answering, and storytelling based on visual content. The model does not support image generation.
37
+
38
+ To fine-tune SmolVLM on a specific task, you can follow [the fine-tuning tutorial](https://github.com/huggingface/smollm/blob/main/vision/finetuning/Smol_VLM_FT.ipynb).
39
+
40
+ ### Technical Summary
41
+
42
+ SmolVLM leverages the lightweight SmolLM2 language model to provide a compact yet powerful multimodal experience. It introduces several changes compared to the larger SmolVLM 2.2B model:
43
+
44
+ - **Image compression:** We introduce a more radical image compression compared to Idefics3 and SmolVLM-2.2B to enable the model to infer faster and use less RAM.
45
+ - **Visual Token Encoding:** SmolVLM-256 uses 64 visual tokens to encode image patches of size 512×512. Larger images are divided into patches, each encoded separately, enhancing efficiency without compromising performance.
46
+ - **New special tokens:** We added new special tokens to divide the subimages. This allows for more efficient tokenization of the images.
47
+ - **Smoller vision encoder:** We went from a 400M parameter siglip vision encoder to a much smaller 93M encoder.
48
+ - **Larger image patches:** We are now passing patches of 512x512 to the vision encoder, instead of 384x384 like the larger SmolVLM. This allows the information to be encoded more efficiently.
49
+
50
+ More details about the training and architecture are available in our technical report.
51
+
52
+ ### How to get started
53
+
54
+ You can use transformers to load, infer and fine-tune SmolVLM.
55
+
56
+ ```python
57
+ import torch
58
+ from PIL import Image
59
+ from transformers import AutoProcessor, AutoModelForVision2Seq
60
+ from transformers.image_utils import load_image
61
+
62
+ DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
63
+
64
+ # Load images
65
+ image = load_image("https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg")
66
+
67
+ # Initialize processor and model
68
+ processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-256M-Instruct")
69
+ model = AutoModelForVision2Seq.from_pretrained(
70
+ "HuggingFaceTB/SmolVLM-256M-Instruct",
71
+ torch_dtype=torch.bfloat16,
72
+ _attn_implementation="flash_attention_2" if DEVICE == "cuda" else "eager",
73
+ ).to(DEVICE)
74
+
75
+ # Create input messages
76
+ messages = [
77
+ {
78
+ "role": "user",
79
+ "content": [
80
+ {"type": "image"},
81
+ {"type": "text", "text": "Can you describe this image?"}
82
+ ]
83
+ },
84
+ ]
85
+
86
+ # Prepare inputs
87
+ prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
88
+ inputs = processor(text=prompt, images=[image], return_tensors="pt")
89
+ inputs = inputs.to(DEVICE)
90
+
91
+ # Generate outputs
92
+ generated_ids = model.generate(**inputs, max_new_tokens=500)
93
+ generated_texts = processor.batch_decode(
94
+ generated_ids,
95
+ skip_special_tokens=True,
96
+ )
97
+
98
+ print(generated_texts[0])
99
+ """
100
+ Assistant: The image depicts a large, historic statue of liberty, located in New York City. The statue is a green, cylindrical structure with a human figure at the top, holding a torch. The statue is situated on a pedestal that resembles the statue of liberty, which is located on a small island in the middle of a body of water. The water surrounding the island is calm, reflecting the blue sky and the statue.
101
+ In the background, there are several tall buildings, including the Empire State Building, which is visible in the distance. These buildings are made of glass and steel, and they are positioned in a grid-like pattern, giving them a modern look. The sky is clear, with a few clouds visible, indicating fair weather.
102
+ The statue is surrounded by trees, which are green and appear to be healthy. There are also some small structures, possibly houses or buildings, visible in the distance. The overall scene suggests a peaceful and serene environment, typical of a cityscape.
103
+ The image is taken during the daytime, likely during the day of the statue's installation. The lighting is bright, casting a strong shadow on the statue and the water, which enhances the visibility of the statue and the surrounding environment.
104
+ To summarize, the image captures a significant historical statue of liberty, situated on a small island in the middle of a body of water, surrounded by trees and buildings. The sky is clear, with a few clouds visible, indicating fair weather. The statue is green and cylindrical, with a human figure holding a torch, and is surrounded by trees, indicating a peaceful and well-maintained environment. The overall scene is one of tranquility and historical significance.
105
+ """
106
+ ```
107
+
108
+ We also provide ONNX weights for the model, which you can run with ONNX Runtime as follows:
109
+ <details>
110
+
111
+ <summary>Click here to see the sample code</summary>
112
+
113
+ ```python
114
+ from transformers import AutoConfig, AutoProcessor
115
+ from transformers.image_utils import load_image
116
+ import onnxruntime
117
+ import numpy as np
118
+
119
+ # 1. Load models
120
+ ## Load config and processor
121
+ model_id = "HuggingFaceTB/SmolVLM-256M-Instruct"
122
+ config = AutoConfig.from_pretrained(model_id)
123
+ processor = AutoProcessor.from_pretrained(model_id)
124
+
125
+ ## Load sessions
126
+ ## !wget https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct/resolve/main/onnx/vision_encoder.onnx
127
+ ## !wget https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct/resolve/main/onnx/embed_tokens.onnx
128
+ ## !wget https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct/resolve/main/onnx/decoder_model_merged.onnx
129
+ vision_session = onnxruntime.InferenceSession("vision_encoder.onnx")
130
+ embed_session = onnxruntime.InferenceSession("embed_tokens.onnx")
131
+ decoder_session = onnxruntime.InferenceSession("decoder_model_merged.onnx")
132
+
133
+ ## Set config values
134
+ num_key_value_heads = config.text_config.num_key_value_heads
135
+ head_dim = config.text_config.head_dim
136
+ num_hidden_layers = config.text_config.num_hidden_layers
137
+ eos_token_id = config.text_config.eos_token_id
138
+ image_token_id = config.image_token_id
139
+
140
+
141
+ # 2. Prepare inputs
142
+ ## Create input messages
143
+ messages = [
144
+ {
145
+ "role": "user",
146
+ "content": [
147
+ {"type": "image"},
148
+ {"type": "text", "text": "Can you describe this image?"}
149
+ ]
150
+ },
151
+ ]
152
+
153
+ ## Load image and apply processor
154
+ image = load_image("https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg")
155
+ prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
156
+ inputs = processor(text=prompt, images=[image], return_tensors="np")
157
+
158
+ ## Prepare decoder inputs
159
+ batch_size = inputs['input_ids'].shape[0]
160
+ past_key_values = {
161
+ f'past_key_values.{layer}.{kv}': np.zeros([batch_size, num_key_value_heads, 0, head_dim], dtype=np.float32)
162
+ for layer in range(num_hidden_layers)
163
+ for kv in ('key', 'value')
164
+ }
165
+ image_features = None
166
+ input_ids = inputs['input_ids']
167
+ attention_mask = inputs['attention_mask']
168
+ position_ids = np.cumsum(inputs['attention_mask'], axis=-1)
169
+
170
+
171
+ # 3. Generation loop
172
+ max_new_tokens = 1024
173
+ generated_tokens = np.array([[]], dtype=np.int64)
174
+ for i in range(max_new_tokens):
175
+ inputs_embeds = embed_session.run(None, {'input_ids': input_ids})[0]
176
+
177
+ if image_features is None:
178
+ ## Only compute vision features if not already computed
179
+ image_features = vision_session.run(
180
+ ['image_features'], # List of output names or indices
181
+ {
182
+ 'pixel_values': inputs['pixel_values'],
183
+ 'pixel_attention_mask': inputs['pixel_attention_mask'].astype(np.bool_)
184
+ }
185
+ )[0]
186
+
187
+ ## Merge text and vision embeddings
188
+ inputs_embeds[inputs['input_ids'] == image_token_id] = image_features.reshape(-1, image_features.shape[-1])
189
+
190
+ logits, *present_key_values = decoder_session.run(None, dict(
191
+ inputs_embeds=inputs_embeds,
192
+ attention_mask=attention_mask,
193
+ position_ids=position_ids,
194
+ **past_key_values,
195
+ ))
196
+
197
+ ## Update values for next generation loop
198
+ input_ids = logits[:, -1].argmax(-1, keepdims=True)
199
+ attention_mask = np.ones_like(input_ids)
200
+ position_ids = position_ids[:, -1:] + 1
201
+ for j, key in enumerate(past_key_values):
202
+ past_key_values[key] = present_key_values[j]
203
+
204
+ generated_tokens = np.concatenate([generated_tokens, input_ids], axis=-1)
205
+ if (input_ids == eos_token_id).all():
206
+ break
207
+
208
+ ## (Optional) Streaming
209
+ print(processor.decode(input_ids[0]), end='')
210
+ print()
211
+
212
+ # 4. Output result
213
+ print(processor.batch_decode(generated_tokens))
214
+ ```
215
+
216
+ Example output:
217
+ ```
218
+ The image depicts a large, historic statue of Liberty situated on a small island in a body of water. The statue is a green, cylindrical structure with a human figure at the top, which is the actual statue of Liberty. The statue is mounted on a pedestal that is supported by a cylindrical tower. The pedestal is rectangular and appears to be made of stone or a similar material. The statue is surrounded by a large, flat, rectangular area that is likely a base for the statue.
219
+
220
+ In the background, there is a cityscape with a variety of buildings, including skyscrapers and high-rise buildings. The sky is clear with a gradient of colors, transitioning from a pale blue at the top to a deeper blue at the bottom. The buildings are mostly modern, with a mix of glass and concrete. The buildings are densely packed, with many skyscrapers and high-rise buildings visible.
221
+
222
+ There are trees and greenery visible on the left side of the image, indicating that the statue is located near a park or a park area. The water in the foreground is calm, with small ripples indicating that the statue is in the water.
223
+
224
+ The overall scene suggests a peaceful and serene environment, likely a public park or a park area in a city. The statue is likely a representation of liberty, representing the city's commitment to freedom and democracy.
225
+
226
+ ### Analysis and Description:
227
+
228
+ #### Statue of Liberty:
229
+ - **Location**: The statue is located on a small island in a body of water.
230
+ - **Statue**: The statue is a green cylindrical structure with a human figure at the top, which is the actual statue of Liberty.
231
+ - **Pedestal**: The pedestal is rectangular and supports the statue.
232
+ - **Pedestrian**: The pedestal is surrounded by a flat rectangular area.
233
+ - **Water**: The water is calm, with small ripples indicating that the statue is in the water.
234
+
235
+ #### Cityscape:
236
+ - **Buildings**: The buildings are modern, with a mix of glass and concrete.
237
+ - **Sky**: The sky is clear with a gradient of colors, transitioning from a pale blue at the top to a deeper blue at the bottom.
238
+ - **Trees**: There are trees and greenery visible on the left side of the image, indicating that the statue is located near a park or a park area.
239
+
240
+ #### Environment:
241
+ - **Water**: The water is calm, with small ripples indicating that the statue is in the water.
242
+ - **Sky**: The sky is clear with a gradient of colors, transitioning from a pale blue at the top to a deeper blue at the bottom.
243
+
244
+ ### Conclusion:
245
+ The image depicts a peaceful and serene public park or park area in a city, with the statue of Liberty prominently featured. The cityscape in the background includes modern buildings and a clear sky, suggesting a well-maintained public space.<end_of_utterance>
246
+ ```
247
+
248
+ </details>
249
+
250
+ ### Model optimizations
251
+
252
+ **Precision**: For better performance, load and run the model in half-precision (`torch.bfloat16`) if your hardware supports it.
253
+
254
+ ```python
255
+ from transformers import AutoModelForVision2Seq
256
+ import torch
257
+
258
+ model = AutoModelForVision2Seq.from_pretrained(
259
+ "HuggingFaceTB/SmolVLM-Instruct",
260
+ torch_dtype=torch.bfloat16
261
+ ).to("cuda")
262
+ ```
263
+
264
+ You can also load SmolVLM with 4/8-bit quantization using bitsandbytes, torchao or Quanto. Refer to [this page](https://huggingface.co/docs/transformers/en/main_classes/quantization) for other options.
265
+
266
+ ```python
267
+ from transformers import AutoModelForVision2Seq, BitsAndBytesConfig
268
+ import torch
269
+
270
+ quantization_config = BitsAndBytesConfig(load_in_8bit=True)
271
+ model = AutoModelForVision2Seq.from_pretrained(
272
+ "HuggingFaceTB/SmolVLM-Instruct",
273
+ quantization_config=quantization_config,
274
+ )
275
+ ```
276
+
277
+ **Vision Encoder Efficiency**: Adjust the image resolution by setting `size={"longest_edge": N*512}` when initializing the processor, where N is your desired value. The default `N=4` works well, which results in input images of
278
+ size 2048×2048. Decreasing N can save GPU memory and is appropriate for lower-resolution images. This is also useful if you want to fine-tune on videos.
279
+
280
+
281
+ ## Misuse and Out-of-scope Use
282
+
283
+ SmolVLM is not intended for high-stakes scenarios or critical decision-making processes that affect an individual's well-being or livelihood. The model may produce content that appears factual but may not be accurate. Misuse includes, but is not limited to:
284
+
285
+ - Prohibited Uses:
286
+ - Evaluating or scoring individuals (e.g., in employment, education, credit)
287
+ - Critical automated decision-making
288
+ - Generating unreliable factual content
289
+ - Malicious Activities:
290
+ - Spam generation
291
+ - Disinformation campaigns
292
+ - Harassment or abuse
293
+ - Unauthorized surveillance
294
+
295
+ ### License
296
+
297
+ SmolVLM is built upon [SigLIP](https://huggingface.co/google/siglip-base-patch16-512) as image encoder and [SmolLM2](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct) for text decoder part.
298
+
299
+ We release the SmolVLM checkpoints under the Apache 2.0 license.
300
+
301
+ ## Training Details
302
+
303
+ ### Training Data
304
+
305
+ The training data comes from [The Cauldron](https://huggingface.co/datasets/HuggingFaceM4/the_cauldron) and [Docmatix](https://huggingface.co/datasets/HuggingFaceM4/Docmatix) datasets, with emphasis on document understanding (25%) and image captioning (18%), while maintaining balanced coverage across other crucial capabilities like visual reasoning, chart comprehension, and general instruction following.
306
+ <img src="https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct/resolve/main/mixture_the_cauldron.png" alt="Example Image" style="width:90%;" />
307
+
308
+
309
+
310
+ ## Evaluation
311
+
312
+ | Size | Mathvista | MMMU | OCRBench | MMStar | AI2D | ChartQA_Test | Science_QA | TextVQA Val | DocVQA Val |
313
+ |-------|-----------|------|----------|--------|-------|--------------|------------|-------------|------------|
314
+ | 256M | 35.9 | 28.3 | 52.6 | 34.6 | 47 | 55.8 | 73.6 | 49.9 | 58.3 |
315
+ | 500M | 40.1 | 33.7 | 61 | 38.3 | 59.5 | 63.2 | 79.7 | 60.5 | 70.5 |
316
+ | 2.2B | 43.9 | 38.3 | 65.5 | 41.8 | 64 | 71.6 | 84.5 | 72.1 | 79.7 |
317
+
318
+
319
+ # Citation information
320
+ You can cite us in the following way:
321
+ ```bibtex
322
+ @unpublished{marafioti2025smolvlm,
323
+ title = {SmolVLM: Redefining small and efficient multimodal models},
324
+ author = {Marafioti, Andr\'{e}s and Zohar, Orr and Farr\'{e}, Miquel and Noyan, Merve and Bakouch, Elie and Cuenca, Pedro and Zakka, Cyril and Ben Allal, Loubna and Lozhkov, Anton and Tazi, Nouamane and Srivastav, Vaibhav and Lochner, Joshua and Larcher, Hugo and Morlon, Mathieu and Tunstall, Lewis and von Werra, Leandro and Wolf, Thomas},
325
+ year = {2025},
326
+ }
327
+ ```
added_tokens.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<end_of_utterance>": 49279,
3
+ "<fake_token_around_image>": 49189,
4
+ "<global-img>": 49152,
5
+ "<image>": 49190,
6
+ "<row_1_col_1>": 49153,
7
+ "<row_1_col_2>": 49154,
8
+ "<row_1_col_3>": 49155,
9
+ "<row_1_col_4>": 49156,
10
+ "<row_1_col_5>": 49157,
11
+ "<row_1_col_6>": 49158,
12
+ "<row_2_col_1>": 49159,
13
+ "<row_2_col_2>": 49160,
14
+ "<row_2_col_3>": 49161,
15
+ "<row_2_col_4>": 49162,
16
+ "<row_2_col_5>": 49163,
17
+ "<row_2_col_6>": 49164,
18
+ "<row_3_col_1>": 49165,
19
+ "<row_3_col_2>": 49166,
20
+ "<row_3_col_3>": 49167,
21
+ "<row_3_col_4>": 49168,
22
+ "<row_3_col_5>": 49169,
23
+ "<row_3_col_6>": 49170,
24
+ "<row_4_col_1>": 49171,
25
+ "<row_4_col_2>": 49172,
26
+ "<row_4_col_3>": 49173,
27
+ "<row_4_col_4>": 49174,
28
+ "<row_4_col_5>": 49175,
29
+ "<row_4_col_6>": 49176,
30
+ "<row_5_col_1>": 49177,
31
+ "<row_5_col_2>": 49178,
32
+ "<row_5_col_3>": 49179,
33
+ "<row_5_col_4>": 49180,
34
+ "<row_5_col_5>": 49181,
35
+ "<row_5_col_6>": 49182,
36
+ "<row_6_col_1>": 49183,
37
+ "<row_6_col_2>": 49184,
38
+ "<row_6_col_3>": 49185,
39
+ "<row_6_col_4>": 49186,
40
+ "<row_6_col_5>": 49187,
41
+ "<row_6_col_6>": 49188,
42
+ "<|reserved_special_token_0|>": 49191,
43
+ "<|reserved_special_token_10|>": 49201,
44
+ "<|reserved_special_token_11|>": 49202,
45
+ "<|reserved_special_token_12|>": 49203,
46
+ "<|reserved_special_token_13|>": 49204,
47
+ "<|reserved_special_token_14|>": 49205,
48
+ "<|reserved_special_token_15|>": 49206,
49
+ "<|reserved_special_token_16|>": 49207,
50
+ "<|reserved_special_token_17|>": 49208,
51
+ "<|reserved_special_token_18|>": 49209,
52
+ "<|reserved_special_token_19|>": 49210,
53
+ "<|reserved_special_token_1|>": 49192,
54
+ "<|reserved_special_token_20|>": 49211,
55
+ "<|reserved_special_token_21|>": 49212,
56
+ "<|reserved_special_token_22|>": 49213,
57
+ "<|reserved_special_token_23|>": 49214,
58
+ "<|reserved_special_token_24|>": 49215,
59
+ "<|reserved_special_token_25|>": 49216,
60
+ "<|reserved_special_token_26|>": 49217,
61
+ "<|reserved_special_token_27|>": 49218,
62
+ "<|reserved_special_token_28|>": 49219,
63
+ "<|reserved_special_token_29|>": 49220,
64
+ "<|reserved_special_token_2|>": 49193,
65
+ "<|reserved_special_token_30|>": 49221,
66
+ "<|reserved_special_token_31|>": 49222,
67
+ "<|reserved_special_token_32|>": 49223,
68
+ "<|reserved_special_token_33|>": 49224,
69
+ "<|reserved_special_token_34|>": 49225,
70
+ "<|reserved_special_token_35|>": 49226,
71
+ "<|reserved_special_token_36|>": 49227,
72
+ "<|reserved_special_token_37|>": 49228,
73
+ "<|reserved_special_token_38|>": 49229,
74
+ "<|reserved_special_token_39|>": 49230,
75
+ "<|reserved_special_token_3|>": 49194,
76
+ "<|reserved_special_token_40|>": 49231,
77
+ "<|reserved_special_token_41|>": 49232,
78
+ "<|reserved_special_token_42|>": 49233,
79
+ "<|reserved_special_token_43|>": 49234,
80
+ "<|reserved_special_token_44|>": 49235,
81
+ "<|reserved_special_token_45|>": 49236,
82
+ "<|reserved_special_token_46|>": 49237,
83
+ "<|reserved_special_token_47|>": 49238,
84
+ "<|reserved_special_token_48|>": 49239,
85
+ "<|reserved_special_token_49|>": 49240,
86
+ "<|reserved_special_token_4|>": 49195,
87
+ "<|reserved_special_token_50|>": 49241,
88
+ "<|reserved_special_token_51|>": 49242,
89
+ "<|reserved_special_token_52|>": 49243,
90
+ "<|reserved_special_token_53|>": 49244,
91
+ "<|reserved_special_token_54|>": 49245,
92
+ "<|reserved_special_token_55|>": 49246,
93
+ "<|reserved_special_token_56|>": 49247,
94
+ "<|reserved_special_token_57|>": 49248,
95
+ "<|reserved_special_token_58|>": 49249,
96
+ "<|reserved_special_token_59|>": 49250,
97
+ "<|reserved_special_token_5|>": 49196,
98
+ "<|reserved_special_token_60|>": 49251,
99
+ "<|reserved_special_token_61|>": 49252,
100
+ "<|reserved_special_token_62|>": 49253,
101
+ "<|reserved_special_token_63|>": 49254,
102
+ "<|reserved_special_token_64|>": 49255,
103
+ "<|reserved_special_token_65|>": 49256,
104
+ "<|reserved_special_token_66|>": 49257,
105
+ "<|reserved_special_token_67|>": 49258,
106
+ "<|reserved_special_token_68|>": 49259,
107
+ "<|reserved_special_token_69|>": 49260,
108
+ "<|reserved_special_token_6|>": 49197,
109
+ "<|reserved_special_token_70|>": 49261,
110
+ "<|reserved_special_token_71|>": 49262,
111
+ "<|reserved_special_token_72|>": 49263,
112
+ "<|reserved_special_token_73|>": 49264,
113
+ "<|reserved_special_token_74|>": 49265,
114
+ "<|reserved_special_token_75|>": 49266,
115
+ "<|reserved_special_token_76|>": 49267,
116
+ "<|reserved_special_token_77|>": 49268,
117
+ "<|reserved_special_token_78|>": 49269,
118
+ "<|reserved_special_token_79|>": 49270,
119
+ "<|reserved_special_token_7|>": 49198,
120
+ "<|reserved_special_token_80|>": 49271,
121
+ "<|reserved_special_token_81|>": 49272,
122
+ "<|reserved_special_token_82|>": 49273,
123
+ "<|reserved_special_token_83|>": 49274,
124
+ "<|reserved_special_token_84|>": 49275,
125
+ "<|reserved_special_token_85|>": 49276,
126
+ "<|reserved_special_token_86|>": 49277,
127
+ "<|reserved_special_token_87|>": 49278,
128
+ "<|reserved_special_token_8|>": 49199,
129
+ "<|reserved_special_token_9|>": 49200
130
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,271 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Idefics3ForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 49190,
6
+ "model_type": "idefics3",
7
+ "scale_factor": 4,
8
+ "text_config": {
9
+ "_attn_implementation_autoset": false,
10
+ "_flash_attn_2_enabled": true,
11
+ "_name_or_path": "None",
12
+ "add_cross_attention": false,
13
+ "architectures": [
14
+ "VLlama3ForCausalLM"
15
+ ],
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "bad_words_ids": null,
19
+ "begin_suppress_tokens": null,
20
+ "bos_token_id": 1,
21
+ "chunk_size_feed_forward": 0,
22
+ "cross_attention_hidden_size": null,
23
+ "decoder_start_token_id": null,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "early_stopping": false,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": 2,
29
+ "exponential_decay_length_penalty": null,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "head_dim": 64,
34
+ "hidden_act": "silu",
35
+ "hidden_size": 576,
36
+ "id2label": {
37
+ "0": "LABEL_0",
38
+ "1": "LABEL_1"
39
+ },
40
+ "initializer_range": 0.041666666666666664,
41
+ "intermediate_size": 1536,
42
+ "is_decoder": false,
43
+ "is_encoder_decoder": false,
44
+ "is_llama_config": true,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1
48
+ },
49
+ "length_penalty": 1.0,
50
+ "max_length": 20,
51
+ "max_position_embeddings": 8192,
52
+ "min_length": 0,
53
+ "mlp_bias": false,
54
+ "model_type": "llama",
55
+ "neftune_noise_alpha": 0.0,
56
+ "no_repeat_ngram_size": 0,
57
+ "num_attention_heads": 9,
58
+ "num_beam_groups": 1,
59
+ "num_beams": 1,
60
+ "num_hidden_layers": 30,
61
+ "num_key_value_heads": 3,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": 2,
67
+ "perceiver_config": {
68
+ "_attn_implementation_autoset": false,
69
+ "_name_or_path": "",
70
+ "add_cross_attention": false,
71
+ "architectures": null,
72
+ "attention_dropout": 0.0,
73
+ "bad_words_ids": null,
74
+ "begin_suppress_tokens": null,
75
+ "bos_token_id": null,
76
+ "chunk_size_feed_forward": 0,
77
+ "cross_attention_hidden_size": null,
78
+ "decoder_start_token_id": null,
79
+ "diversity_penalty": 0.0,
80
+ "do_sample": false,
81
+ "early_stopping": false,
82
+ "encoder_no_repeat_ngram_size": 0,
83
+ "eos_token_id": null,
84
+ "exponential_decay_length_penalty": null,
85
+ "finetuning_task": null,
86
+ "forced_bos_token_id": null,
87
+ "forced_eos_token_id": null,
88
+ "hidden_act": "silu",
89
+ "id2label": {
90
+ "0": "LABEL_0",
91
+ "1": "LABEL_1"
92
+ },
93
+ "is_decoder": false,
94
+ "is_encoder_decoder": false,
95
+ "label2id": {
96
+ "LABEL_0": 0,
97
+ "LABEL_1": 1
98
+ },
99
+ "length_penalty": 1.0,
100
+ "max_length": 20,
101
+ "min_length": 0,
102
+ "model_type": "vllama3",
103
+ "no_repeat_ngram_size": 0,
104
+ "num_beam_groups": 1,
105
+ "num_beams": 1,
106
+ "num_key_value_heads": 1,
107
+ "num_return_sequences": 1,
108
+ "output_attentions": false,
109
+ "output_hidden_states": false,
110
+ "output_scores": false,
111
+ "pad_token_id": null,
112
+ "prefix": null,
113
+ "problem_type": null,
114
+ "pruned_heads": {},
115
+ "qk_layer_norms_perceiver": false,
116
+ "remove_invalid_values": false,
117
+ "repetition_penalty": 1.0,
118
+ "resampler_depth": 6,
119
+ "resampler_head_dim": 96,
120
+ "resampler_n_heads": 16,
121
+ "resampler_n_latents": 64,
122
+ "return_dict": true,
123
+ "return_dict_in_generate": false,
124
+ "sep_token_id": null,
125
+ "suppress_tokens": null,
126
+ "task_specific_params": null,
127
+ "temperature": 1.0,
128
+ "tf_legacy_loss": false,
129
+ "tie_encoder_decoder": false,
130
+ "tie_word_embeddings": true,
131
+ "tokenizer_class": null,
132
+ "top_k": 50,
133
+ "top_p": 1.0,
134
+ "torch_dtype": null,
135
+ "torchscript": false,
136
+ "transformers_version": "4.46.0",
137
+ "typical_p": 1.0,
138
+ "use_bfloat16": false
139
+ },
140
+ "pixel_shuffle_factor": 4,
141
+ "prefix": null,
142
+ "pretraining_tp": 1,
143
+ "problem_type": null,
144
+ "pruned_heads": {},
145
+ "qk_layer_norms": false,
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "rms_norm_eps": 1e-05,
151
+ "rope_interleaved": false,
152
+ "rope_scaling": null,
153
+ "rope_theta": 100000,
154
+ "sep_token_id": null,
155
+ "suppress_tokens": null,
156
+ "task_specific_params": null,
157
+ "temperature": 1.0,
158
+ "tf_legacy_loss": false,
159
+ "tie_encoder_decoder": false,
160
+ "tie_word_embeddings": false,
161
+ "tokenizer_class": null,
162
+ "top_k": 50,
163
+ "top_p": 1.0,
164
+ "torch_dtype": "bfloat16",
165
+ "torchscript": false,
166
+ "transformers.js_config": {
167
+ "kv_cache_dtype": {
168
+ "fp16": "float16",
169
+ "q4f16": "float16"
170
+ }
171
+ },
172
+ "typical_p": 1.0,
173
+ "use_bfloat16": false,
174
+ "use_cache": true,
175
+ "use_resampler": false,
176
+ "vocab_size": 49280
177
+ },
178
+ "tie_word_embeddings": false,
179
+ "torch_dtype": "bfloat16",
180
+ "transformers_version": "4.46.0",
181
+ "transformers.js_config": {
182
+ "kv_cache_dtype": {
183
+ "q4f16": "float16",
184
+ "fp16": "float16"
185
+ }
186
+ },
187
+ "use_cache": true,
188
+ "vision_config": {
189
+ "use_base_siglip": true,
190
+ "_attn_implementation_autoset": false,
191
+ "_name_or_path": "",
192
+ "add_cross_attention": false,
193
+ "architectures": null,
194
+ "attention_dropout": 0.0,
195
+ "bad_words_ids": null,
196
+ "begin_suppress_tokens": null,
197
+ "bos_token_id": null,
198
+ "chunk_size_feed_forward": 0,
199
+ "cross_attention_hidden_size": null,
200
+ "decoder_start_token_id": null,
201
+ "diversity_penalty": 0.0,
202
+ "do_sample": false,
203
+ "early_stopping": false,
204
+ "encoder_no_repeat_ngram_size": 0,
205
+ "eos_token_id": null,
206
+ "exponential_decay_length_penalty": null,
207
+ "finetuning_task": null,
208
+ "forced_bos_token_id": null,
209
+ "forced_eos_token_id": null,
210
+ "hidden_act": "gelu_pytorch_tanh",
211
+ "hidden_size": 768,
212
+ "id2label": {
213
+ "0": "LABEL_0",
214
+ "1": "LABEL_1"
215
+ },
216
+ "image_size": 512,
217
+ "initializer_range": 0.02,
218
+ "intermediate_size": 3072,
219
+ "is_decoder": false,
220
+ "is_encoder_decoder": false,
221
+ "label2id": {
222
+ "LABEL_0": 0,
223
+ "LABEL_1": 1
224
+ },
225
+ "layer_norm_eps": 1e-06,
226
+ "length_penalty": 1.0,
227
+ "max_image_size": {
228
+ "longest_edge": 512
229
+ },
230
+ "max_length": 20,
231
+ "min_length": 0,
232
+ "model_type": "idefics3",
233
+ "no_repeat_ngram_size": 0,
234
+ "num_attention_heads": 12,
235
+ "num_beam_groups": 1,
236
+ "num_beams": 1,
237
+ "num_channels": 3,
238
+ "num_hidden_layers": 12,
239
+ "num_return_sequences": 1,
240
+ "output_attentions": false,
241
+ "output_hidden_states": false,
242
+ "output_scores": false,
243
+ "pad_token_id": null,
244
+ "patch_size": 16,
245
+ "prefix": null,
246
+ "problem_type": null,
247
+ "pruned_heads": {},
248
+ "remove_invalid_values": false,
249
+ "repetition_penalty": 1.0,
250
+ "return_dict": true,
251
+ "return_dict_in_generate": false,
252
+ "sep_token_id": null,
253
+ "size": {
254
+ "longest_edge": 2048
255
+ },
256
+ "suppress_tokens": null,
257
+ "task_specific_params": null,
258
+ "temperature": 1.0,
259
+ "tf_legacy_loss": false,
260
+ "tie_encoder_decoder": false,
261
+ "tie_word_embeddings": false,
262
+ "tokenizer_class": null,
263
+ "top_k": 50,
264
+ "top_p": 1.0,
265
+ "torch_dtype": null,
266
+ "torchscript": false,
267
+ "typical_p": 1.0,
268
+ "use_bfloat16": false
269
+ },
270
+ "vocab_size": 49280
271
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 49279,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.46.0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2817946df1e3b4c99ad196995338edc1c1c0d8423d3b5153da77f67f8c2efc0a
3
+ size 540971996
onnx/decoder_model_merged_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b8ba5c04aa524c2a3cdcba4825df38b24c04619ecffa6c6afcc77220f565bb3
3
+ size 78486591
onnx/decoder_model_merged_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bb75887b9f71b0f61cc1621dcc47c711f5b61fbf64a895500fe2e577f2929c2
3
+ size 270745856
onnx/decoder_model_merged_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5580b6f2f49fa7c034cd67ba12196b11d5ab5162d7318baf48ead494e45944ca
3
+ size 137553014
onnx/decoder_model_merged_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f67dd06edf4edbbfeca36f79aaa1b3ea934a2b166d462b3b152788ec3232cd
3
+ size 86894595
onnx/decoder_model_merged_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b297c76610889394757b8baacda12ce27b23747afafd3ddf5b7fbb183f699704
3
+ size 77366233
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d19fafe563a1277492b94a562eda7c5c01a27373b2ee4cb4e716713d261a93
3
+ size 137553128
onnx/decoder_model_merged_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d19fafe563a1277492b94a562eda7c5c01a27373b2ee4cb4e716713d261a93
3
+ size 137553128
onnx/embed_tokens.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68ea4058524059ed0e2873fdbc4f33b93e13ae3d3204938d32d0566d390ae00
3
+ size 113541419
onnx/embed_tokens_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47ed7029703cff586fd719d70251324766a6591c8a58d315076b1781a65fc900
3
+ size 113541438
onnx/embed_tokens_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:019af59078b8e4775216dd278c66574c39bfefa36cab68573db64d7ac7a11691
3
+ size 56770946
onnx/embed_tokens_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b919b829fe2bf225e42431230c56891116f0149e5170e36c99bcc0cfae0d2ef
3
+ size 28385824
onnx/embed_tokens_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47ed7029703cff586fd719d70251324766a6591c8a58d315076b1781a65fc900
3
+ size 113541438
onnx/embed_tokens_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d810e0849eda8128be2d9cf1a2be9ca0bd8e5bfbe5bf972f60ea8e2a566f6bfe
3
+ size 56770965
onnx/embed_tokens_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b919b829fe2bf225e42431230c56891116f0149e5170e36c99bcc0cfae0d2ef
3
+ size 28385824
onnx/embed_tokens_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b919b829fe2bf225e42431230c56891116f0149e5170e36c99bcc0cfae0d2ef
3
+ size 28385824
onnx/vision_encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e27ad810eabfa7c881b409e1ca357e7a951541019add228ff73c72718fcf6218
3
+ size 374316497
onnx/vision_encoder_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d2b29e46fa0de326b63e92e751561cf28180d597ad0ad0859f92bf598944352
3
+ size 58034739
onnx/vision_encoder_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:275c41d775508b7f7410580c4aaf67583a34acf23c31259effa8e53f67e8d9ae
3
+ size 187294693
onnx/vision_encoder_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d534ab668d3563e6d1d809bbbf1ff18308ded48651178614dbcc4a1de13d16f7
3
+ size 94247927
onnx/vision_encoder_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95814e6629ec465e7cf98a44edcee67abc06d41faa0d1acc410cf8a956cab488
3
+ size 63784987
onnx/vision_encoder_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c301dc0cbc79c8c23badc699129b47d05ba044e2274ca8a94681fcd4205fc1
3
+ size 55037584
onnx/vision_encoder_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f82adc84246fbfe8651038470166385452682cc889538f5106544e622e5f1595
3
+ size 94247969
onnx/vision_encoder_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f82adc84246fbfe8651038470166385452682cc889538f5106544e622e5f1595
3
+ size 94247969
preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_image_splitting": true,
4
+ "do_normalize": true,
5
+ "do_pad": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Idefics3ImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "max_image_size": {
20
+ "longest_edge": 512
21
+ },
22
+ "processor_class": "Idefics3Processor",
23
+ "resample": 1,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "longest_edge": 2048
27
+ }
28
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_len": 64,
3
+ "processor_class": "Idefics3Processor"
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<fake_token_around_image>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<image>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<end_of_utterance>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "bos_token": {
26
+ "content": "<|im_start|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "eos_token": {
33
+ "content": "<|im_end|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "pad_token": {
40
+ "content": "<|im_end|>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "unk_token": {
47
+ "content": "<|endoftext|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ }
53
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,1182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "49152": {
141
+ "content": "<global-img>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49153": {
149
+ "content": "<row_1_col_1>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49154": {
157
+ "content": "<row_1_col_2>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "49155": {
165
+ "content": "<row_1_col_3>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "49156": {
173
+ "content": "<row_1_col_4>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "49157": {
181
+ "content": "<row_1_col_5>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "49158": {
189
+ "content": "<row_1_col_6>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "49159": {
197
+ "content": "<row_2_col_1>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "49160": {
205
+ "content": "<row_2_col_2>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "49161": {
213
+ "content": "<row_2_col_3>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "49162": {
221
+ "content": "<row_2_col_4>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "49163": {
229
+ "content": "<row_2_col_5>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "49164": {
237
+ "content": "<row_2_col_6>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "49165": {
245
+ "content": "<row_3_col_1>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "49166": {
253
+ "content": "<row_3_col_2>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "49167": {
261
+ "content": "<row_3_col_3>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "49168": {
269
+ "content": "<row_3_col_4>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "49169": {
277
+ "content": "<row_3_col_5>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "49170": {
285
+ "content": "<row_3_col_6>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "49171": {
293
+ "content": "<row_4_col_1>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "49172": {
301
+ "content": "<row_4_col_2>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "49173": {
309
+ "content": "<row_4_col_3>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "49174": {
317
+ "content": "<row_4_col_4>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "49175": {
325
+ "content": "<row_4_col_5>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "49176": {
333
+ "content": "<row_4_col_6>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "49177": {
341
+ "content": "<row_5_col_1>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "49178": {
349
+ "content": "<row_5_col_2>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "49179": {
357
+ "content": "<row_5_col_3>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "49180": {
365
+ "content": "<row_5_col_4>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "49181": {
373
+ "content": "<row_5_col_5>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "49182": {
381
+ "content": "<row_5_col_6>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "49183": {
389
+ "content": "<row_6_col_1>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "49184": {
397
+ "content": "<row_6_col_2>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "49185": {
405
+ "content": "<row_6_col_3>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "49186": {
413
+ "content": "<row_6_col_4>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "49187": {
421
+ "content": "<row_6_col_5>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "49188": {
429
+ "content": "<row_6_col_6>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "49189": {
437
+ "content": "<fake_token_around_image>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "49190": {
445
+ "content": "<image>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "49191": {
453
+ "content": "<|reserved_special_token_0|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "49192": {
461
+ "content": "<|reserved_special_token_1|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "49193": {
469
+ "content": "<|reserved_special_token_2|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "49194": {
477
+ "content": "<|reserved_special_token_3|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "49195": {
485
+ "content": "<|reserved_special_token_4|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "49196": {
493
+ "content": "<|reserved_special_token_5|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "49197": {
501
+ "content": "<|reserved_special_token_6|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "49198": {
509
+ "content": "<|reserved_special_token_7|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "49199": {
517
+ "content": "<|reserved_special_token_8|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "49200": {
525
+ "content": "<|reserved_special_token_9|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "49201": {
533
+ "content": "<|reserved_special_token_10|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "49202": {
541
+ "content": "<|reserved_special_token_11|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "49203": {
549
+ "content": "<|reserved_special_token_12|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "49204": {
557
+ "content": "<|reserved_special_token_13|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "49205": {
565
+ "content": "<|reserved_special_token_14|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "49206": {
573
+ "content": "<|reserved_special_token_15|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "49207": {
581
+ "content": "<|reserved_special_token_16|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "49208": {
589
+ "content": "<|reserved_special_token_17|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "49209": {
597
+ "content": "<|reserved_special_token_18|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "49210": {
605
+ "content": "<|reserved_special_token_19|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "49211": {
613
+ "content": "<|reserved_special_token_20|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "49212": {
621
+ "content": "<|reserved_special_token_21|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "49213": {
629
+ "content": "<|reserved_special_token_22|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "49214": {
637
+ "content": "<|reserved_special_token_23|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "49215": {
645
+ "content": "<|reserved_special_token_24|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "49216": {
653
+ "content": "<|reserved_special_token_25|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "49217": {
661
+ "content": "<|reserved_special_token_26|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "49218": {
669
+ "content": "<|reserved_special_token_27|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "49219": {
677
+ "content": "<|reserved_special_token_28|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "49220": {
685
+ "content": "<|reserved_special_token_29|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "49221": {
693
+ "content": "<|reserved_special_token_30|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "49222": {
701
+ "content": "<|reserved_special_token_31|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "49223": {
709
+ "content": "<|reserved_special_token_32|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "49224": {
717
+ "content": "<|reserved_special_token_33|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "49225": {
725
+ "content": "<|reserved_special_token_34|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "49226": {
733
+ "content": "<|reserved_special_token_35|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "49227": {
741
+ "content": "<|reserved_special_token_36|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "49228": {
749
+ "content": "<|reserved_special_token_37|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "49229": {
757
+ "content": "<|reserved_special_token_38|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "49230": {
765
+ "content": "<|reserved_special_token_39|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "49231": {
773
+ "content": "<|reserved_special_token_40|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "49232": {
781
+ "content": "<|reserved_special_token_41|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "49233": {
789
+ "content": "<|reserved_special_token_42|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "49234": {
797
+ "content": "<|reserved_special_token_43|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "49235": {
805
+ "content": "<|reserved_special_token_44|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "49236": {
813
+ "content": "<|reserved_special_token_45|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "49237": {
821
+ "content": "<|reserved_special_token_46|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "49238": {
829
+ "content": "<|reserved_special_token_47|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "49239": {
837
+ "content": "<|reserved_special_token_48|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "49240": {
845
+ "content": "<|reserved_special_token_49|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "49241": {
853
+ "content": "<|reserved_special_token_50|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "49242": {
861
+ "content": "<|reserved_special_token_51|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "49243": {
869
+ "content": "<|reserved_special_token_52|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "49244": {
877
+ "content": "<|reserved_special_token_53|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "49245": {
885
+ "content": "<|reserved_special_token_54|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "49246": {
893
+ "content": "<|reserved_special_token_55|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "49247": {
901
+ "content": "<|reserved_special_token_56|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "49248": {
909
+ "content": "<|reserved_special_token_57|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "49249": {
917
+ "content": "<|reserved_special_token_58|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "49250": {
925
+ "content": "<|reserved_special_token_59|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "49251": {
933
+ "content": "<|reserved_special_token_60|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "49252": {
941
+ "content": "<|reserved_special_token_61|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "49253": {
949
+ "content": "<|reserved_special_token_62|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "49254": {
957
+ "content": "<|reserved_special_token_63|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "49255": {
965
+ "content": "<|reserved_special_token_64|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "49256": {
973
+ "content": "<|reserved_special_token_65|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "49257": {
981
+ "content": "<|reserved_special_token_66|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "49258": {
989
+ "content": "<|reserved_special_token_67|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "49259": {
997
+ "content": "<|reserved_special_token_68|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "49260": {
1005
+ "content": "<|reserved_special_token_69|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "49261": {
1013
+ "content": "<|reserved_special_token_70|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "49262": {
1021
+ "content": "<|reserved_special_token_71|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "49263": {
1029
+ "content": "<|reserved_special_token_72|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "49264": {
1037
+ "content": "<|reserved_special_token_73|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "49265": {
1045
+ "content": "<|reserved_special_token_74|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "49266": {
1053
+ "content": "<|reserved_special_token_75|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "49267": {
1061
+ "content": "<|reserved_special_token_76|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "49268": {
1069
+ "content": "<|reserved_special_token_77|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "49269": {
1077
+ "content": "<|reserved_special_token_78|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "49270": {
1085
+ "content": "<|reserved_special_token_79|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "49271": {
1093
+ "content": "<|reserved_special_token_80|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "49272": {
1101
+ "content": "<|reserved_special_token_81|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "49273": {
1109
+ "content": "<|reserved_special_token_82|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "49274": {
1117
+ "content": "<|reserved_special_token_83|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "49275": {
1125
+ "content": "<|reserved_special_token_84|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "49276": {
1133
+ "content": "<|reserved_special_token_85|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "49277": {
1141
+ "content": "<|reserved_special_token_86|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "49278": {
1149
+ "content": "<|reserved_special_token_87|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "49279": {
1157
+ "content": "<end_of_utterance>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ }
1164
+ },
1165
+ "additional_special_tokens": [
1166
+ "<fake_token_around_image>",
1167
+ "<image>",
1168
+ "<end_of_utterance>"
1169
+ ],
1170
+ "bos_token": "<|im_start|>",
1171
+ "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
1172
+ "clean_up_tokenization_spaces": false,
1173
+ "eos_token": "<end_of_utterance>",
1174
+ "legacy": false,
1175
+ "model_max_length": 8192,
1176
+ "pad_token": "<|im_end|>",
1177
+ "processor_class": "Idefics3Processor",
1178
+ "tokenizer_class": "GPT2Tokenizer",
1179
+ "truncation_side": "left",
1180
+ "unk_token": "<|endoftext|>",
1181
+ "vocab_size": 49280
1182
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff