Text Generation
Transformers
Safetensors
qwen3_5
image-text-to-text
qwen
code
software-engineering
swe-bench
sft
tool-use
agents
conversational
Instructions to use AxiaoDBL/qwen3.5-4b-swebench-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AxiaoDBL/qwen3.5-4b-swebench-sft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AxiaoDBL/qwen3.5-4b-swebench-sft") 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("AxiaoDBL/qwen3.5-4b-swebench-sft") model = AutoModelForMultimodalLM.from_pretrained("AxiaoDBL/qwen3.5-4b-swebench-sft", 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 AxiaoDBL/qwen3.5-4b-swebench-sft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AxiaoDBL/qwen3.5-4b-swebench-sft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AxiaoDBL/qwen3.5-4b-swebench-sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/AxiaoDBL/qwen3.5-4b-swebench-sft
- SGLang
How to use AxiaoDBL/qwen3.5-4b-swebench-sft 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 "AxiaoDBL/qwen3.5-4b-swebench-sft" \ --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": "AxiaoDBL/qwen3.5-4b-swebench-sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "AxiaoDBL/qwen3.5-4b-swebench-sft" \ --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": "AxiaoDBL/qwen3.5-4b-swebench-sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use AxiaoDBL/qwen3.5-4b-swebench-sft with Docker Model Runner:
docker model run hf.co/AxiaoDBL/qwen3.5-4b-swebench-sft
What teacher model and issue pool were used for the model training?
#1
by SYHDSG - opened
Great work. What teacher model and issue pool did you use?
SYHDSG changed discussion status to closed
SYHDSG changed discussion status to open
SYHDSG changed discussion title from What teacher model and issue pool did you use? to What teacher model and issue pool were used for the model training?
Great work. What teacher model and issue pool did you use?
Thanks. I used Deepseek-V4-Flash as teacher model and the subset of SWE-Lego datasets for rollout.