Instructions to use 6cf/Qwen3.5-4B-SWE-SFT-Coldstart with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 6cf/Qwen3.5-4B-SWE-SFT-Coldstart with Transformers:

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

pipe = pipeline("image-text-to-text", model="6cf/Qwen3.5-4B-SWE-SFT-Coldstart")
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("6cf/Qwen3.5-4B-SWE-SFT-Coldstart")
model = AutoModelForMultimodalLM.from_pretrained("6cf/Qwen3.5-4B-SWE-SFT-Coldstart", 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 6cf/Qwen3.5-4B-SWE-SFT-Coldstart with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "6cf/Qwen3.5-4B-SWE-SFT-Coldstart"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "6cf/Qwen3.5-4B-SWE-SFT-Coldstart",
		"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/6cf/Qwen3.5-4B-SWE-SFT-Coldstart

SGLang

How to use 6cf/Qwen3.5-4B-SWE-SFT-Coldstart 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 "6cf/Qwen3.5-4B-SWE-SFT-Coldstart" \
    --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": "6cf/Qwen3.5-4B-SWE-SFT-Coldstart",
		"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 "6cf/Qwen3.5-4B-SWE-SFT-Coldstart" \
        --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": "6cf/Qwen3.5-4B-SWE-SFT-Coldstart",
		"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 6cf/Qwen3.5-4B-SWE-SFT-Coldstart with Docker Model Runner:
```
docker model run hf.co/6cf/Qwen3.5-4B-SWE-SFT-Coldstart
```

Qwen3.5-4B-SWE-SFT-Coldstart

Qwen3.5-4B-SWE-SFT-Coldstart is an agentic software-engineering cold-start checkpoint based on Qwen/Qwen3.5-4B.

The model was supervised fine-tuned on successful software-engineering agent trajectories generated by DeepSeek-V4-Flash and DeepSeek-V4-Pro. The trajectories use a Claude-Code-compatible tool harness and were executed in isolated SWE-Gym repository environments. Only trajectories accepted by an execution-based verifier were retained for supervised fine-tuning.

This repository contains the merged model weights. It is the SFT cold-start checkpoint before subsequent reinforcement learning.

Agent tool format

The checkpoint uses the native Qwen3.5 XML tool-call format. A typical call has the following shape:

<tool_call>
<function=Read>
<parameter=file_path>/testbed/package/module.py</parameter>
</function>
</tool_call>

Do not convert this checkpoint to a legacy Hermes JSON tool-call template at inference time. Use the included tokenizer and chat_template.jinja.

Training summary

Base model: Qwen/Qwen3.5-4B
Training method: LoRA supervised fine-tuning, merged into the base model
Teacher models: DeepSeek-V4-Flash, DeepSeek-V4-Pro
Domain: executable software-engineering agent trajectories
Environment: SWE-Gym repositories with a Claude-Code-compatible tool interface
Data filtering: execution-verifier-positive trajectories only
Training framework: MS-SWIFT
Precision: BF16
LoRA rank: 32
LoRA alpha: 64
Context length used for SFT: 32,768 tokens
Packing: disabled

Tool outputs and environment responses were retained as conversation context but were not intended as model-generated supervision. The supervised targets are assistant turns, including native Qwen3.5 tool calls and final responses.

Loading with Transformers

Use a recent Transformers release with Qwen3.5 support.

from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "6cf/Qwen3.5-4B-SWE-SFT-Coldstart"

processor = AutoProcessor.from_pretrained(
    model_id,
    trust_remote_code=True,
)
model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

For text-only agent inference, the same processor and model can be used with a text conversation and tool schemas passed through the included chat template.

Downloads last month: 13

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for 6cf/Qwen3.5-4B-SWE-SFT-Coldstart

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(559)

this model