Instructions to use laion/SweSmith-8B-SFT-NoRope-step58 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use laion/SweSmith-8B-SFT-NoRope-step58 with Transformers:

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

pipe = pipeline("text-generation", model="laion/SweSmith-8B-SFT-NoRope-step58")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("laion/SweSmith-8B-SFT-NoRope-step58")
model = AutoModelForCausalLM.from_pretrained("laion/SweSmith-8B-SFT-NoRope-step58")
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 Settings

vLLM

How to use laion/SweSmith-8B-SFT-NoRope-step58 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "laion/SweSmith-8B-SFT-NoRope-step58"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "laion/SweSmith-8B-SFT-NoRope-step58",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/laion/SweSmith-8B-SFT-NoRope-step58

SGLang

How to use laion/SweSmith-8B-SFT-NoRope-step58 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 "laion/SweSmith-8B-SFT-NoRope-step58" \
    --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": "laion/SweSmith-8B-SFT-NoRope-step58",
		"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 "laion/SweSmith-8B-SFT-NoRope-step58" \
        --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": "laion/SweSmith-8B-SFT-NoRope-step58",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use laion/SweSmith-8B-SFT-NoRope-step58 with Docker Model Runner:
```
docker model run hf.co/laion/SweSmith-8B-SFT-NoRope-step58
```

SweSmith-8B-SFT-NoRope-step58

RL-trained Qwen3-8B on SWEsmith tasks (32k context, no rope scaling, 58 steps). Beats the SFT base model on dev_set_71 (pass@1 0.227 vs 0.213) and SWE-bench 100 (0.220 vs 0.210).

Training Details

Base model: laion/r2egym-nl2bash-stack-bugsseq-fixthink-again (Qwen3-8B SFT)
Training method: RLOO-N (Reinforcement Learning with Leave-One-Out baselines)
Training data: 2,500 SWEsmith tasks (oracle-verified, 120s timeout)
Framework: BenSkyRL + Harbor

Downloads last month: 9

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for laion/SweSmith-8B-SFT-NoRope-step58

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Finetuned

laion/r2egym-nl2bash-stack-bugsseq-fixthink-again

Finetuned

(10)

this model