Instructions to use bunny127/SophiaVL-R1-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bunny127/SophiaVL-R1-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="bunny127/SophiaVL-R1-7B") 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, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("bunny127/SophiaVL-R1-7B") model = AutoModelForImageTextToText.from_pretrained("bunny127/SophiaVL-R1-7B") 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
- vLLM
How to use bunny127/SophiaVL-R1-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bunny127/SophiaVL-R1-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bunny127/SophiaVL-R1-7B", "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/bunny127/SophiaVL-R1-7B
- SGLang
How to use bunny127/SophiaVL-R1-7B 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 "bunny127/SophiaVL-R1-7B" \ --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": "bunny127/SophiaVL-R1-7B", "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 "bunny127/SophiaVL-R1-7B" \ --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": "bunny127/SophiaVL-R1-7B", "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 bunny127/SophiaVL-R1-7B with Docker Model Runner:
docker model run hf.co/bunny127/SophiaVL-R1-7B
Upload 4 files
Browse files- added_tokens.json +24 -0
- chat_template.json +3 -0
- config.json +65 -0
- generation_config.json +6 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"hidden_act": "silu",
|
| 8 |
+
"hidden_size": 3584,
|
| 9 |
+
"image_token_id": 151655,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 18944,
|
| 12 |
+
"max_position_embeddings": 128000,
|
| 13 |
+
"max_window_layers": 28,
|
| 14 |
+
"model_type": "qwen2_5_vl",
|
| 15 |
+
"num_attention_heads": 28,
|
| 16 |
+
"num_hidden_layers": 28,
|
| 17 |
+
"num_key_value_heads": 4,
|
| 18 |
+
"pad_token_id": 151643,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": {
|
| 21 |
+
"mrope_section": [
|
| 22 |
+
16,
|
| 23 |
+
24,
|
| 24 |
+
24
|
| 25 |
+
],
|
| 26 |
+
"rope_type": "default",
|
| 27 |
+
"type": "default"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"sliding_window": 32768,
|
| 31 |
+
"tie_word_embeddings": false,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.51.3",
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"use_sliding_window": false,
|
| 36 |
+
"video_token_id": 151656,
|
| 37 |
+
"vision_config": {
|
| 38 |
+
"depth": 32,
|
| 39 |
+
"fullatt_block_indexes": [
|
| 40 |
+
7,
|
| 41 |
+
15,
|
| 42 |
+
23,
|
| 43 |
+
31
|
| 44 |
+
],
|
| 45 |
+
"hidden_act": "silu",
|
| 46 |
+
"hidden_size": 1280,
|
| 47 |
+
"in_channels": 3,
|
| 48 |
+
"in_chans": 3,
|
| 49 |
+
"intermediate_size": 3420,
|
| 50 |
+
"model_type": "qwen2_5_vl",
|
| 51 |
+
"num_heads": 16,
|
| 52 |
+
"out_hidden_size": 3584,
|
| 53 |
+
"patch_size": 14,
|
| 54 |
+
"spatial_merge_size": 2,
|
| 55 |
+
"spatial_patch_size": 14,
|
| 56 |
+
"temporal_patch_size": 2,
|
| 57 |
+
"tokens_per_second": 2,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"window_size": 112
|
| 60 |
+
},
|
| 61 |
+
"vision_end_token_id": 151653,
|
| 62 |
+
"vision_start_token_id": 151652,
|
| 63 |
+
"vision_token_id": 151654,
|
| 64 |
+
"vocab_size": 152064
|
| 65 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 151645,
|
| 4 |
+
"pad_token_id": 151643,
|
| 5 |
+
"transformers_version": "4.51.3"
|
| 6 |
+
}
|