Instructions to use laion/rl_pymethods2test-r2egym_terminus-structured with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use laion/rl_pymethods2test-r2egym_terminus-structured with Transformers:

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

pipe = pipeline("text-generation", model="laion/rl_pymethods2test-r2egym_terminus-structured")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("laion/rl_pymethods2test-r2egym_terminus-structured")
model = AutoModelForCausalLM.from_pretrained("laion/rl_pymethods2test-r2egym_terminus-structured")
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

vLLM

How to use laion/rl_pymethods2test-r2egym_terminus-structured with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "laion/rl_pymethods2test-r2egym_terminus-structured"
# 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/rl_pymethods2test-r2egym_terminus-structured",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/laion/rl_pymethods2test-r2egym_terminus-structured

SGLang

How to use laion/rl_pymethods2test-r2egym_terminus-structured 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/rl_pymethods2test-r2egym_terminus-structured" \
    --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/rl_pymethods2test-r2egym_terminus-structured",
		"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/rl_pymethods2test-r2egym_terminus-structured" \
        --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/rl_pymethods2test-r2egym_terminus-structured",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use laion/rl_pymethods2test-r2egym_terminus-structured with Docker Model Runner:
```
docker model run hf.co/laion/rl_pymethods2test-r2egym_terminus-structured
```

rl_pymethods2test-r2egym_terminus-structured

RL-trained Qwen3-8B with structured tool calls (terminus-structured agent).

Training Pipeline

SFT (r2egym+nl2bash+swesmith) → RL mixed dataset (37 steps) → RL full r2egym (55 steps) → RL pymethods2test (156 steps, full epoch)

Key Results

SWEBench-100 pass@3: 37-42% (depending on eval run)
Pymethods2test pass@8: 91-97%
SWEBench in-train eval: up to 14 fully solved at various checkpoints
Training on test-writing (pymethods) maintains code-editing ability (SWEBench)

Training Details

Base model: laion/r2egym-nl2bash-stack-bugsseq-fixthink-again
Agent: terminus-structured (bash, view, edit, create, search tools)
Algorithm: RLOO-N
Learning rate: 1e-5
Context: 32k (24k input + 8k output)
Framework: BenSkyRL + Harbor (JSC HPC)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("laion/rl_pymethods2test-r2egym_terminus-structured")
tokenizer = AutoTokenizer.from_pretrained("laion/rl_pymethods2test-r2egym_terminus-structured")

Downloads last month: 10

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for laion/rl_pymethods2test-r2egym_terminus-structured

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Finetuned

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

Finetuned

(10)

this model