Image-Text-to-Text
Transformers
Safetensors
qwen3_5
thinking_modes
qwen3.5
grape
vision
multimodal
instruct
chat
coding
math
science
reasoning
creative_writing
roleplay
conversational
Instructions to use SL-AI/GRaPE-2.5-Quasar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SL-AI/GRaPE-2.5-Quasar with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="SL-AI/GRaPE-2.5-Quasar") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("SL-AI/GRaPE-2.5-Quasar") model = AutoModelForMultimodalLM.from_pretrained("SL-AI/GRaPE-2.5-Quasar", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SL-AI/GRaPE-2.5-Quasar with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SL-AI/GRaPE-2.5-Quasar" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SL-AI/GRaPE-2.5-Quasar", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/SL-AI/GRaPE-2.5-Quasar
- SGLang
How to use SL-AI/GRaPE-2.5-Quasar with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "SL-AI/GRaPE-2.5-Quasar" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SL-AI/GRaPE-2.5-Quasar", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "SL-AI/GRaPE-2.5-Quasar" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SL-AI/GRaPE-2.5-Quasar", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use SL-AI/GRaPE-2.5-Quasar with Docker Model Runner:
docker model run hf.co/SL-AI/GRaPE-2.5-Quasar
Upload folder using huggingface_hub
Browse files- model-00014-of-00018.safetensors +3 -0
- model-00015-of-00018.safetensors +3 -0
- model-00016-of-00018.safetensors +3 -0
- model-00017-of-00018.safetensors +3 -0
- model-00018-of-00018.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +21 -0
- tokenizer.json +3 -0
- tokenizer_config.json +305 -0
- video_preprocessor_config.json +21 -0
- vocab.json +0 -0
model-00014-of-00018.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bdec42b1e1f09bc19f1e1db2d8b63e0171c3f20713097c1110af1b24bdbbbdc
|
| 3 |
+
size 3979553696
|
model-00015-of-00018.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8508f3a803058f2d571f2a14afa0e80ff3163ca3f2ea35e84a580e06887c207a
|
| 3 |
+
size 2108759344
|
model-00016-of-00018.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3e26cb4b69b3f472984f1af5efbe9ea37f4c4d6e6c0c8f690630de8d68e4fd3
|
| 3 |
+
size 3979564040
|
model-00017-of-00018.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d7d16dd2b5442d1206ff6e2775b83a2c6be8714c4629a181d9e5d0771ff04bf
|
| 3 |
+
size 2108759344
|
model-00018-of-00018.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d3479509e21494658f9b64d317f5ea8e55c4025d28c702d6c4d0b356ce8ea06
|
| 3 |
+
size 3392197344
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3
|
| 3 |
+
size 12809320
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,305 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"248044": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"248045": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"248046": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"248047": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"248048": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"248049": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"248050": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"248051": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"248052": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"248053": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"248054": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"248055": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"248056": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"248057": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"248058": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"248059": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"248060": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"248061": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"248062": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"248063": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"248064": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"248065": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"248066": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"248067": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"248068": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"248069": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
},
|
| 213 |
+
"248070": {
|
| 214 |
+
"content": "<|audio_start|>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"248071": {
|
| 222 |
+
"content": "<|audio_end|>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"248072": {
|
| 230 |
+
"content": "<tts_pad>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"248073": {
|
| 238 |
+
"content": "<tts_text_bos>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
"248074": {
|
| 246 |
+
"content": "<tts_text_eod>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": true
|
| 252 |
+
},
|
| 253 |
+
"248075": {
|
| 254 |
+
"content": "<tts_text_bos_single>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": true
|
| 260 |
+
},
|
| 261 |
+
"248076": {
|
| 262 |
+
"content": "<|audio_pad|>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": true
|
| 268 |
+
}
|
| 269 |
+
},
|
| 270 |
+
"additional_special_tokens": [
|
| 271 |
+
"<|im_start|>",
|
| 272 |
+
"<|im_end|>",
|
| 273 |
+
"<|object_ref_start|>",
|
| 274 |
+
"<|object_ref_end|>",
|
| 275 |
+
"<|box_start|>",
|
| 276 |
+
"<|box_end|>",
|
| 277 |
+
"<|quad_start|>",
|
| 278 |
+
"<|quad_end|>",
|
| 279 |
+
"<|vision_start|>",
|
| 280 |
+
"<|vision_end|>",
|
| 281 |
+
"<|vision_pad|>",
|
| 282 |
+
"<|image_pad|>",
|
| 283 |
+
"<|video_pad|>"
|
| 284 |
+
],
|
| 285 |
+
"bos_token": null,
|
| 286 |
+
"chat_template": "{%- set _tool_format = tool_call_format if tool_call_format is defined else 'xml' %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- set add_vision_id = add_vision_id if add_vision_id is defined else false %}\n{%- set enable_thinking = enable_thinking if enable_thinking is defined else true %}\n{%- set auto_disable_thinking_with_tools = auto_disable_thinking_with_tools if auto_disable_thinking_with_tools is defined else false %}\n{%- set _preserve_thinking = preserve_thinking if preserve_thinking is defined else true %}\n{%- set max_tool_arg_chars = max_tool_arg_chars if max_tool_arg_chars is defined else 0 %}\n{%- set max_tool_response_chars = max_tool_response_chars if max_tool_response_chars is defined else 0 %}\n{%- set _has_tools = (tools is defined and tools and tools is iterable and tools is not mapping) %}\n{%- set ns_state = namespace(thinking=enable_thinking) %}\n{%- if auto_disable_thinking_with_tools and _has_tools %}\n {%- set ns_state.thinking = false %}\n{%- endif %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if item is mapping %}\n {%- if item.type == 'image' or 'image' in item or 'image_url' in item %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif item.type == 'video' or 'video' in item %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- else %}\n {{- item | string }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set _first_role = messages[0].role %}\n{%- if _first_role == 'system' or _first_role == 'developer' %}\n {%- set _sys_msg = messages[0] %}\n {%- set _msgs = messages[1:] %}\n{%- else %}\n {%- set _sys_msg = none %}\n {%- set _msgs = messages %}\n{%- endif %}\n{%- set _sc = '' %}\n{%- if _sys_msg is not none %}\n {%- set _sc = render_content(_sys_msg.content, false, true) | trim %}\n {%- set _sc = _sc.split('<|think_off|>') | join('') | trim %}\n {%- set _sc = _sc.split('<|think_on|>') | join('') | trim %}\n{%- endif %}\n{%- if _has_tools %}\n {{- '<|im_start|>system\\n' }}\n {{- '# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>' }}\n {%- for tool in tools %}\n {{- '\\n' }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- '\\n</tools>' }}\n {%- set tool_instructions %}\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n{%- if _tool_format == 'json' %}\n<think>\nBrief explanation of tool call\n</think>\n<tool_call>\n{\"name\": \"example_function_name\", \"arguments\": {\"example_parameter_1\": \"value_1\", \"example_parameter_2\": \"This is the value for the second parameter\"}}\n</tool_call>\n{%- else %}\n<think>\nBrief explanation of tool call\n</think>\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n{%- endif %}\n<IMPORTANT>\nReminder:\n- You can use the <think></think> block to plan your next tool call OR to synthesize data and formulate your final response to the user.\n- ALL explanation and reasoning MUST be placed strictly inside the <think></think> block.\n{%- if _tool_format == 'json' %}\n- Function calls MUST follow the specified format: a single JSON object with \"name\" and \"arguments\" keys inside <tool_call></tool_call> XML tags.\n{%- else %}\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags.\n{%- endif %}\n- If you choose to call a tool, you MUST output the <tool_call> block IMMEDIATELY after thinking, with NO conversational text before it.\n{%- if _tool_format == 'json' %}\n- The <tool_call> tag MUST be at the very beginning of a new line, with NO spaces or indentation before it.\n{%- else %}\n- The <tool_call> and <function> tags MUST be at the very beginning of a new line, with NO spaces or indentation before them.\n{%- endif %}\n- To call multiple functions, output a separate, completely closed <tool_call></tool_call> block for EACH function. Do NOT nest <tool_call> blocks.\n- If you have all necessary data, provide your final answer directly to the user without any tool call.\n</IMPORTANT>\n {%- endset %}\n {{- '\\n\\n' ~ tool_instructions | trim }}\n {%- if _sc %}\n {{- '\\n\\n' + _sc }}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if _sc %}\n {{- '<|im_start|>system\\n' + _sc + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set _last_idx = _msgs | length - 1 %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=_last_idx) %}\n{%- for message in _msgs[::-1] %}\n {%- set index = (_msgs | length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == 'user' %}\n {%- set _rc = render_content(message.content, false) | trim %}\n {%- if not (_rc.startswith('<tool_response>') and _rc.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {%- if _last_idx > 50 %}\n {%- set ns.last_query_index = _last_idx %}\n {%- else %}\n {%- set ns.last_query_index = 0 %}\n {%- endif %}\n{%- endif %}\n{%- set ns2 = namespace(prev_role='', consecutive_failures=0) %}\n{%- for message in _msgs %}\n {%- set is_system = (message.role == \"system\" or message.role == \"developer\") %}\n {%- set content = render_content(message.content, true, is_system) | trim %}\n {%- if is_system or message.role == 'user' %}\n {%- if '<|think_off|>' in content %}\n {%- set ns_state.thinking = false %}\n {%- set content = content.split('<|think_off|>') | join('') | trim %}\n {%- elif '<|think_on|>' in content %}\n {%- set ns_state.thinking = true %}\n {%- set content = content.split('<|think_on|>') | join('') | trim %}\n {%- endif %}\n {%- endif %}\n {%- if is_system %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- elif message.role == 'user' %}\n {%- set ns2.consecutive_failures = 0 %}\n {{- '<|im_start|>user\\n' + content + '<|im_end|>\\n' }}\n {%- elif message.role == 'assistant' %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- set reasoning_content = message.reasoning_content | string %}\n {%- endif %}\n {%- elif message.thinking is defined and message.thinking is not none %}\n {%- if message.thinking is string %}\n {%- set reasoning_content = message.thinking %}\n {%- else %}\n {%- set reasoning_content = message.thinking | string %}\n {%- endif %}\n {%- else %}\n {%- set _think_end = '' %}\n {%- if content.startswith('</think>') %}\n {%- set _think_end = '</think>' %}\n {%- elif content.startswith('</thinking>') %}\n {%- set _think_end = '</thinking>' %}\n {%- elif '\\n</think>' in content %}\n {%- set _think_end = '\\n</think>' %}\n {%- elif '\\n</thinking>' in content %}\n {%- set _think_end = '\\n</thinking>' %}\n {%- elif '\\n</ think>' in content %}\n {%- set _think_end = '\\n</ think>' %}\n {%- elif '\\n</think >' in content %}\n {%- set _think_end = '\\n</think >' %}\n {%- endif %}\n {%- if _think_end %}\n {%- if 'thinking' in _think_end %}\n {%- set _think_start = '<thinking>' %}\n {%- else %}\n {%- set _think_start = '<think>' %}\n {%- endif %}\n {%- set reasoning_content = content.split(_think_end)[0].rstrip('\\n') %}\n {%- if _think_start in reasoning_content %}\n {%- set reasoning_content = reasoning_content.split(_think_start)[-1].lstrip('\\n') %}\n {%- endif %}\n {%- set content = content.split(_think_end)[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content | trim %}\n {%- if (_preserve_thinking or loop.index0 > ns.last_query_index) and reasoning_content %}\n {{- '<|im_start|>assistant\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>assistant\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls is defined and message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined and tool_call.function is not none %}\n {%- set tc = tool_call.function %}\n {%- else %}\n {%- set tc = tool_call %}\n {%- endif %}\n {%- if _tool_format == 'json' %}\n {%- if not loop.first or content | trim %}\n {{- '\\n\\n' }}\n {%- endif %}\n {%- set _args = '{}' %}\n {%- if tc.arguments is defined and tc.arguments is not none %}\n {%- if tc.arguments is mapping %}\n {%- set _args = tc.arguments | tojson %}\n {%- elif tc.arguments is string and tc.arguments %}\n {%- set _args = tc.arguments %}\n {%- endif %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": ' }}{{- tc.name | tojson }}{{- ', \"arguments\": ' }}{{- _args }}{{- '}\\n</tool_call>' }}\n {%- else %}\n {%- if loop.first %}\n {%- if content | trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tc.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tc.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n\\n<tool_call>\\n<function=' + tc.name + '>\\n' }}\n {%- endif %}\n {%- if tc.arguments is defined and tc.arguments is not none %}\n {%- if tc.arguments is mapping %}\n {%- for args_name, args_value in tc.arguments.items() %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- if args_value is mapping or (args_value is sequence and args_value is not string) %}\n {%- set _av = args_value | tojson %}\n {%- else %}\n {%- set _av = args_value | string %}\n {%- endif %}\n {%- if max_tool_arg_chars > 0 and _av | length > max_tool_arg_chars %}\n {{- _av[:max_tool_arg_chars] + '\\n[TRUNCATED \u2014 original length ' ~ (_av | length | string) ~ ' chars]' }}\n {%- else %}\n {{- _av }}\n {%- endif %}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- elif tc.arguments is string and tc.arguments %}\n {{- tc.arguments }}\n {%- endif %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == 'tool' %}\n {%- set _content_lower = content | lower %}\n {%- set _content_head = _content_lower[:80] %}\n {%- if content | length < 500 and '$ ' not in content and 'took ' not in _content_lower and ('\"error\":' in _content_head or 'error:' in _content_head or 'err!' in _content_head or 'fatal:' in _content_head or 'exception:' in _content_head or 'traceback' in _content_head or 'command not found' in _content_head or 'invalid syntax' in _content_head or 'failed to' in _content_head) %}\n {%- set ns2.consecutive_failures = ns2.consecutive_failures + 1 %}\n {%- else %}\n {%- set ns2.consecutive_failures = 0 %}\n {%- endif %}\n {%- if ns2.prev_role != 'tool' %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {%- if max_tool_response_chars > 0 and content | length > max_tool_response_chars %}\n {%- set content = content[:max_tool_response_chars] + '\\n[TRUNCATED \u2014 original length ' ~ (content | length | string) ~ ' chars]' %}\n {%- endif %}\n {{- '\\n<tool_response>\\n' + content }}\n {%- if ns2.consecutive_failures >= 2 %}\n {{- '\\n\\nSYSTEM WARNING: ' ~ ns2.consecutive_failures ~ ' consecutive tool errors detected. Your previous approach is incorrect. You MUST use a fundamentally different approach or corrected arguments.' }}\n {%- elif ns2.consecutive_failures == 1 %}\n {{- '\\n\\nSYSTEM WARNING: The previous tool call returned an error. Diagnose the failure and retry with completely corrected arguments.' }}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- else %}\n {%- set _next_role = _msgs[loop.index0 + 1].role %}\n {%- if _next_role != 'tool' %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>user\\n[' + message.role + ']: ' + content + '<|im_end|>\\n' }}\n {%- endif %}\n {%- set ns2.prev_role = message.role %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 287 |
+
"clean_up_tokenization_spaces": false,
|
| 288 |
+
"eos_token": "<|im_end|>",
|
| 289 |
+
"errors": "replace",
|
| 290 |
+
"extra_special_tokens": {
|
| 291 |
+
"audio_bos_token": "<|audio_start|>",
|
| 292 |
+
"audio_eos_token": "<|audio_end|>",
|
| 293 |
+
"audio_token": "<|audio_pad|>",
|
| 294 |
+
"image_token": "<|image_pad|>",
|
| 295 |
+
"video_token": "<|video_pad|>",
|
| 296 |
+
"vision_bos_token": "<|vision_start|>",
|
| 297 |
+
"vision_eos_token": "<|vision_end|>"
|
| 298 |
+
},
|
| 299 |
+
"model_max_length": 262144,
|
| 300 |
+
"pad_token": "<|endoftext|>",
|
| 301 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 302 |
+
"split_special_tokens": false,
|
| 303 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 304 |
+
"unk_token": null
|
| 305 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 25165824,
|
| 4 |
+
"shortest_edge": 4096
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|