Instructions to use laion/a2-rl-e2egit_large-50-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use laion/a2-rl-e2egit_large-50-32B with Transformers:

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

pipe = pipeline("text-generation", model="laion/a2-rl-e2egit_large-50-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("laion/a2-rl-e2egit_large-50-32B")
model = AutoModelForCausalLM.from_pretrained("laion/a2-rl-e2egit_large-50-32B", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use laion/a2-rl-e2egit_large-50-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "laion/a2-rl-e2egit_large-50-32B"
# 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/a2-rl-e2egit_large-50-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/laion/a2-rl-e2egit_large-50-32B

SGLang

How to use laion/a2-rl-e2egit_large-50-32B 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/a2-rl-e2egit_large-50-32B" \
    --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/a2-rl-e2egit_large-50-32B",
		"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/a2-rl-e2egit_large-50-32B" \
        --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/a2-rl-e2egit_large-50-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use laion/a2-rl-e2egit_large-50-32B with Docker Model Runner:
```
docker model run hf.co/laion/a2-rl-e2egit_large-50-32B
```

a2-rl-e2egit_large — step 50

RL fine-tune of Qwen3-32B on the e2egit-large task distribution (end-to-end git operations). Training via SkyRL/GRPO on Jupiter (GH200, 16 nodes). Best-reward exported checkpoint.

Training metrics (step 50)

reward/avg_raw_reward: 0.8828
reward/avg_pass_at_8: 0.891 (estimated)
Peak reward across run: 0.9238 @ step 41

Hyperparameters

Algorithm: RLOO-N (GRPO variant)
LR: 9e-6, epochs: 2, max_steps: 60
train_batch_size: 64, n_samples_per_prompt: 8
max_prompt_length: 32768, strategy: fsdp2
Dataset: exp_rpt_e2egit-large

Downloads last month: 8

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for laion/a2-rl-e2egit_large-50-32B

Base model

Qwen/Qwen3-32B

Finetuned

(525)

this model