Instructions to use Allen8/TVC-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Allen8/TVC-7B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Allen8/TVC-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("Allen8/TVC-7B")
model = AutoModelForImageTextToText.from_pretrained("Allen8/TVC-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 Settings

vLLM

How to use Allen8/TVC-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Allen8/TVC-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": "Allen8/TVC-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/Allen8/TVC-7B

SGLang

How to use Allen8/TVC-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 "Allen8/TVC-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": "Allen8/TVC-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 "Allen8/TVC-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": "Allen8/TVC-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 Allen8/TVC-7B with Docker Model Runner:
```
docker model run hf.co/Allen8/TVC-7B
```

Update pipeline tag, add project page link, quick start and other tags

by nielsr HF Staff - opened Mar 21, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+54

-2

Files changed (1) hide show

README.md +54 -2

README.md CHANGED Viewed

@@ -1,14 +1,18 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: Qwen/Qwen2-VL-7B-Instruct
 tags:
 - llama-factory
 - full
 - generated_from_trainer
 model-index:
 - name: TVC-7B
   results: []
 ---
 ## Model Summary
@@ -16,10 +20,10 @@ model-index:
 The TVC models are 7B parameter models based on Qwen2-VL-7B-Instruct model with a context window of 8K tokens.
 - **Repository:** https://github.com/sun-hailong/TVC
 - **Languages:** English, Chinese
 - **Paper:** https://arxiv.org/abs/2503.13360
 ### Model Architecture
 - **Architecture:** Qwen2-VL-7B-Instruct
@@ -39,6 +43,54 @@ The TVC models are 7B parameter models based on Qwen2-VL-7B-Instruct model with
 - Datasets 3.1.0
 - Tokenizers 0.20.3
 ## Citation
 ```

 ---
+base_model: Qwen/Qwen2-VL-7B-Instruct
 library_name: transformers
 license: apache-2.0
 tags:
 - llama-factory
 - full
 - generated_from_trainer
+- long-context
+- reasoning
+- multi-modal
 model-index:
 - name: TVC-7B
   results: []
+pipeline_tag: image-text-to-text
 ---
 ## Model Summary
 The TVC models are 7B parameter models based on Qwen2-VL-7B-Instruct model with a context window of 8K tokens.
 - **Repository:** https://github.com/sun-hailong/TVC
+- **Project Page:** https://sun-hailong.github.io/projects/TVC/
 - **Languages:** English, Chinese
 - **Paper:** https://arxiv.org/abs/2503.13360
 ### Model Architecture
 - **Architecture:** Qwen2-VL-7B-Instruct
 - Datasets 3.1.0
 - Tokenizers 0.20.3
+## Quick Start
+```python
+from vllm import LLM, SamplingParams
+from PIL import Image
+model_name = "Allen8/TVC-72B"
+llm = LLM(
+        model=model_name,
+        trust_remote_code=True,
+        tensor_parallel_size=8,
+    )
+question = "Hint: Please answer the question requiring an integer answer and provide the final value, e.g., 1, 2, 3, at the end.
+Question: Subtract all red things. Subtract all tiny matte balls. How many objects are left?
+Please answer the question using a long-chain reasoning style and think step by step."
+placeholder = "<|image_pad|>"
+prompt = ("<|im_start|>system
+You are a helpful assistant.<|im_end|>
+"
+f"<|im_start|>user
+<|vision_start|>{placeholder}<|vision_end|>"
+f"{question}<|im_end|>
+"
+"<|im_start|>assistant
+")
+sampling_params = SamplingParams(
+    temperature=0.0,
+    top_k=1,
+    top_p=1.0,
+    stop_token_ids=[],
+    repetition_penalty=1.05,
+    max_tokens=8192
+)
+image = Image.open("images/case1.png")
+inputs = {
+            "prompt": prompt,
+            "multi_modal_data": {
+                "image": image
+            },
+        }
+outputs = llm.generate([inputs], sampling_params=sampling_params)
+print(outputs[0].outputs[0].text)
+```
 ## Citation
 ```