Instructions to use BurnyCoder/qwen2.5-coder-0.5b-swe-rl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BurnyCoder/qwen2.5-coder-0.5b-swe-rl with Transformers:

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

pipe = pipeline("text-generation", model="BurnyCoder/qwen2.5-coder-0.5b-swe-rl")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BurnyCoder/qwen2.5-coder-0.5b-swe-rl")
model = AutoModelForCausalLM.from_pretrained("BurnyCoder/qwen2.5-coder-0.5b-swe-rl", device_map="auto")
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]:]))

PEFT
How to use BurnyCoder/qwen2.5-coder-0.5b-swe-rl with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BurnyCoder/qwen2.5-coder-0.5b-swe-rl with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BurnyCoder/qwen2.5-coder-0.5b-swe-rl"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BurnyCoder/qwen2.5-coder-0.5b-swe-rl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BurnyCoder/qwen2.5-coder-0.5b-swe-rl

SGLang

How to use BurnyCoder/qwen2.5-coder-0.5b-swe-rl 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 "BurnyCoder/qwen2.5-coder-0.5b-swe-rl" \
    --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": "BurnyCoder/qwen2.5-coder-0.5b-swe-rl",
		"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 "BurnyCoder/qwen2.5-coder-0.5b-swe-rl" \
        --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": "BurnyCoder/qwen2.5-coder-0.5b-swe-rl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BurnyCoder/qwen2.5-coder-0.5b-swe-rl with Docker Model Runner:
```
docker model run hf.co/BurnyCoder/qwen2.5-coder-0.5b-swe-rl
```

Qwen2.5-Coder-0.5B MiniBug-RL

This repository contains the merged output of the MiniBug-RL hidden-unit-test GRPO experiment. It targets single-function Python repair; it is not a repository-scale autonomous software-engineering agent.

Documentation correction

The model, adapter, and measured results were originally published at immutable revision 5b6e22a4c6c01bec95d10e93a0fc78666eb9c543. This later README-only correction fixes metric terminology and narrows claims to what the recorded evidence establishes. It did not rerun training or evaluation. The audited repository documentation is at GitHub commit 902ca72a46bbc55b3154a3e2f1cd5c8cff6ddde2.

Exact lineage

Base: Qwen/Qwen2.5-Coder-0.5B-Instruct at ea3f2471cf1b1f0db85067f1ef93848e38e88c25
Source: https://github.com/BurnyCoder/llm-rl-software-engineering/commit/7027bc55baecc00fad51cbe2b8f030dca2c91c1e
Trainer: TRL GRPO with LoRA rank 16, alpha 32, learning rate 1e-05, seed 42
Selection: train chosen only on the 12-task validation split

Frozen final-test result

Metric	Base	Selected model
Greedy pass@1	0.4167	0.5000
Greedy hidden-test fraction	0.6083	0.6042
Observed sampled success@4	0.8333	0.8333

Observed sampled success@4 is the fraction of tasks with at least one complete repair among exactly four generated samples; it is not an unbiased pass@k estimator.

Paired hidden-test-fraction difference: -0.0042 with paired percentile-bootstrap 95% interval [-0.2917, 0.2625]. The validation learning gate, pre-specified in the producing source commit, passed. These small synthetic-split measurements should not be generalized to SWE-bench.

Frozen external HumanEvalFix result

Metric	Base	Selected model
Greedy pass@1 (164 Python repairs)	0.2256	0.2317
Timeouts	3	4

Protocol: bigcode/humanevalpack at immutable dataset revision 9a41762f73a8cb23bb5811b73d5aab164efcf378, prompt variant humanevalfixdocs-python, greedy n=1. Postprocessing reference: pinned BigCode Python harness. Paired pass@1 difference: 0.0061 with paired percentile-bootstrap 95% interval [-0.0183, 0.0366]. HumanEvalPack examples, candidate outcomes, and scores did not enter the implemented training, reward-computation, checkpoint-selection, or tuning data flows. Its pinned harness source defined the frozen external protocol; public benchmark contamination may still affect both policies. Executable candidates ran under MiniBug-RL's host-enforced 3-second wall-clock deadline around resource-limited isolated Docker, rather than the pinned BigCode Python harness's 10-second limit; treat this as a MiniBug-sandbox measurement, not a directly comparable leaderboard score. Sandbox image: sha256:a869cd1dffb8c87afad1bb1302106cb9f5cb580641c7391bb73f4ab077f140d9. Docker controls are defense in depth, not proof that this runner is safe for arbitrary hostile code. Internal parser/policy rejections and deterministic reward cache hits do not start containers. Paired percentile-bootstrap intervals describe these fixed task samples; they do not by themselves establish broad model quality.

Included evidence

results.json: candidate-level outcomes and aggregates. Its immutable historical key sampled_pass_at_4 denotes the observed four-draw statistic relabeled above.
training_config.json: resolved non-secret configuration.
Producing source commit: implementation used for training and evaluation.

Load the resulting model

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "BurnyCoder/qwen2.5-coder-0.5b-swe-rl"
result_revision = "5b6e22a4c6c01bec95d10e93a0fc78666eb9c543"
tokenizer = AutoTokenizer.from_pretrained(model_id, revision=result_revision)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    revision=result_revision,
    dtype="auto",
)

The separately loadable LoRA adapter and tokenizer are in adapter/. Candidate-level measurements and the resolved configuration are included.

Downloads last month: 431

Safetensors

Model size

0.5B params

Tensor type

BF16

Model tree for BurnyCoder/qwen2.5-coder-0.5b-swe-rl

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-Coder-0.5B

Finetuned

Qwen/Qwen2.5-Coder-0.5B-Instruct

Finetuned

(101)

this model