Instructions to use czlll/Qwen2.5-Coder-32B-CL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use czlll/Qwen2.5-Coder-32B-CL with Transformers:

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

pipe = pipeline("text-generation", model="czlll/Qwen2.5-Coder-32B-CL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("czlll/Qwen2.5-Coder-32B-CL")
model = AutoModelForCausalLM.from_pretrained("czlll/Qwen2.5-Coder-32B-CL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use czlll/Qwen2.5-Coder-32B-CL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "czlll/Qwen2.5-Coder-32B-CL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "czlll/Qwen2.5-Coder-32B-CL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/czlll/Qwen2.5-Coder-32B-CL

SGLang

How to use czlll/Qwen2.5-Coder-32B-CL 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 "czlll/Qwen2.5-Coder-32B-CL" \
    --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": "czlll/Qwen2.5-Coder-32B-CL",
		"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 "czlll/Qwen2.5-Coder-32B-CL" \
        --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": "czlll/Qwen2.5-Coder-32B-CL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use czlll/Qwen2.5-Coder-32B-CL with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for czlll/Qwen2.5-Coder-32B-CL to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for czlll/Qwen2.5-Coder-32B-CL to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for czlll/Qwen2.5-Coder-32B-CL to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="czlll/Qwen2.5-Coder-32B-CL",
    max_seq_length=2048,
)

Docker Model Runner
How to use czlll/Qwen2.5-Coder-32B-CL with Docker Model Runner:
```
docker model run hf.co/czlll/Qwen2.5-Coder-32B-CL
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for LocAgent

This model is described in the paper LocAgent: Graph-Guided LLM Agents for Code Localization. LocAgent uses a graph-based code representation to enable LLMs to perform accurate code localization, significantly improving accuracy compared to existing methods. Notably, the fine-tuned Qwen-2.5-Coder-Instruct-32B model achieves near state-of-the-art performance with a substantial cost reduction.

Code: https://github.com/gersteinlab/LocAgent

How to Use

LocAgent involves two main steps: graph indexing and code localization.

1. Graph Indexing (Optional but Recommended): For efficient batch processing, pre-generate graph indexes for your codebase using dependency_graph/batch_build_graph.py. This script parses the codebase into a graph representation. See the Github README for detailed command-line arguments and setup instructions. Example:

python dependency_graph/batch_build_graph.py \
       --dataset 'czlll/Loc-Bench' \
       --split 'test' \
       --num_processes 50 \
       --download_repo

2. Code Localization: Use auto_search_main.py to perform code localization. This script leverages LLMs to search and locate relevant code entities within the pre-generated graph indexes. See the Github README for detailed command-line arguments and environment variable setup. Example:

python auto_search_main.py \
   --dataset 'czlll/SWE-bench_Lite' \
   --split 'test' \
   --model 'azure/gpt-4o' \
   --localize \
   --merge \
   --output_folder $result_path/location \
   --eval_n_limit 300 \
   --num_processes 50 \
   --use_function_calling \
   --simple_desc

3. Evaluation: After localization, evaluate the results using evaluation.eval_metric.evaluate_results. An example Jupyter Notebook is provided in evaluation/run_evaluation.ipynb.

Citation

@article{chen2025locagent,
  title={LocAgent: Graph-Guided LLM Agents for Code Localization},
  author={Chen, Zhaoling and Tang, Xiangru and Deng, Gangda and Wu, Fang and Wu, Jialong and Jiang, Zhiwei and Prasanna, Viktor and Cohan, Arman and Wang, Xingyao},
  journal={arXiv preprint arXiv:2503.09089},
  year={2025}
}

Downloads last month: 6

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for czlll/Qwen2.5-Coder-32B-CL

Quantizations

1 model

Paper for czlll/Qwen2.5-Coder-32B-CL

LocAgent: Graph-Guided LLM Agents for Code Localization

Paper • 2503.09089 • Published Mar 12, 2025 • 13