Instructions to use carev01/qwen35-4b-graphrag with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use carev01/qwen35-4b-graphrag with Transformers:

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

pipe = pipeline("image-text-to-text", model="carev01/qwen35-4b-graphrag")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("carev01/qwen35-4b-graphrag")
model = AutoModelForMultimodalLM.from_pretrained("carev01/qwen35-4b-graphrag", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use carev01/qwen35-4b-graphrag with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "carev01/qwen35-4b-graphrag"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "carev01/qwen35-4b-graphrag",
		"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/carev01/qwen35-4b-graphrag

SGLang

How to use carev01/qwen35-4b-graphrag 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 "carev01/qwen35-4b-graphrag" \
    --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": "carev01/qwen35-4b-graphrag",
		"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 "carev01/qwen35-4b-graphrag" \
        --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": "carev01/qwen35-4b-graphrag",
		"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 carev01/qwen35-4b-graphrag with Docker Model Runner:
```
docker model run hf.co/carev01/qwen35-4b-graphrag
```

qwen35-4b-graphrag (safetensors)

Fine-tune of Qwen/Qwen3.5-4B for graphiti-core 0.30.1 extraction prompts (graph-rag project).

Provenance of the weights (read before use):

model.safetensors-00001-of-00002.safetensors is the original bf16 export.
model.safetensors-00002-of-00002.safetensors was rebuilt on 2026-10-08 because the original upload was empty: text and MTP tensors were dequantized from carev01/qwen35-4b-graphrag-mtp-gguf (Q8_0) through the exact inverse of llama.cpp's Qwen3.5 converter (verified by a round trip against the converter: 441/441 tensors, max error 6e-8); the vision tower is copied from Qwen/Qwen3.5-4B (untouched by the fine-tune). Those tensors therefore carry Q8_0 rounding (~0.5% relative error), the same precision the GGUF was evaluated at.

Serve with vLLM; thinking off (--default-chat-template-kwargs '{"enable_thinking": false}').

Downloads last month: 26

Safetensors

Model size

5B params

Tensor type

BF16

F32

Model tree for carev01/qwen35-4b-graphrag

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(1099)

this model