Instructions to use lllqaq/Qwen2.5-Coder-7B-SWEsmith-400 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lllqaq/Qwen2.5-Coder-7B-SWEsmith-400 with Transformers:

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

pipe = pipeline("text-generation", model="lllqaq/Qwen2.5-Coder-7B-SWEsmith-400")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lllqaq/Qwen2.5-Coder-7B-SWEsmith-400")
model = AutoModelForCausalLM.from_pretrained("lllqaq/Qwen2.5-Coder-7B-SWEsmith-400")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use lllqaq/Qwen2.5-Coder-7B-SWEsmith-400 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lllqaq/Qwen2.5-Coder-7B-SWEsmith-400"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lllqaq/Qwen2.5-Coder-7B-SWEsmith-400",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lllqaq/Qwen2.5-Coder-7B-SWEsmith-400

SGLang

How to use lllqaq/Qwen2.5-Coder-7B-SWEsmith-400 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 "lllqaq/Qwen2.5-Coder-7B-SWEsmith-400" \
    --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": "lllqaq/Qwen2.5-Coder-7B-SWEsmith-400",
		"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 "lllqaq/Qwen2.5-Coder-7B-SWEsmith-400" \
        --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": "lllqaq/Qwen2.5-Coder-7B-SWEsmith-400",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lllqaq/Qwen2.5-Coder-7B-SWEsmith-400 with Docker Model Runner:
```
docker model run hf.co/lllqaq/Qwen2.5-Coder-7B-SWEsmith-400
```

Qwen2.5-Coder-7B-SWEsmith-400

A full fine-tune of Qwen/Qwen2.5-Coder-7B-Instruct on 400 SWE-agent trajectories from the SWE-smith project, intended for use as a software-engineering agent (SWE-agent / SWE-bench style tasks).

⚠️ Experimental / small-scale. This was trained on only 400 trajectories as a workflow validation run, not a production model. Treat it as a reproducibility / sanity baseline.

Training data

Source: SWE-bench/SWE-smith-trajectories, xml split (the format SWE-agent-LM was trained on).
Subset: first 400 of the 26,076 trajectories (multi-turn agent rollouts, avg ~67 messages/traj).
Format: OpenAI-style messages, supervised on assistant turns only (train_on_input=False).

Method

Full-parameter SFT with torchtune (full_finetune_distributed), using SWE-smith's default 7B config.

Hyperparameter	Value
Base model	Qwen2.5-Coder-7B-Instruct
Optimizer	AdamW (fused), wd=0.01
LR / schedule	1e-4, cosine, 5 warmup steps
Epochs	3
Max seq len	32768
Precision	bf16
Per-device batch	1, grad-accum 4
Hardware	7× A100 80GB (FSDP) → effective batch 28
Total optimizer steps	42
Activation checkpointing	on

Training loss: 0.41 → 0.19 (ep0) → 0.11 (ep1) → 0.085 (ep2). This repo is the epoch 2 checkpoint.

Intended use & limitations

Designed to be served (vLLM / SGLang) behind SWE-agent for automated bug-fixing on repository-level tasks. Given the tiny training set, expect limited generalization; it has not been evaluated on SWE-bench. Inherits the base model's capabilities and biases.