Instructions to use LLucass/GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLucass/GRPO with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LLucass/GRPO")
model = AutoModelForCausalLM.from_pretrained("LLucass/GRPO")
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 LLucass/GRPO with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/LLucass/GRPO

SGLang

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

Docker Model Runner
How to use LLucass/GRPO with Docker Model Runner:
```
docker model run hf.co/LLucass/GRPO
```

LLucass commited on Jul 1, 2025

Commit

253ba01

verified ·

1 Parent(s): e019249

Training in progress, step 50

Browse files

Files changed (3) hide show

config.json +1 -1
model.safetensors +1 -1
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -21,7 +21,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
   "use_cache": false,
   "use_mrope": false,
   "use_sliding_window": false,

   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
   "use_cache": false,
   "use_mrope": false,
   "use_sliding_window": false,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:451dbc65abbaed7de6a9d48583e71f709e8b20fc0103cc8635add7ca15367613
 size 3554214752

 version https://git-lfs.github.com/spec/v1
+oid sha256:4448914707878f19b6c33781f2f66b0d0cbca4db8219442254db02ea6f820d0b
 size 3554214752

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dec060f7b56bd55bb36d708a3c66849f741c4f6a9b0bd2b8056da9fcaa5f2f9
 size 8120

 version https://git-lfs.github.com/spec/v1
+oid sha256:1200ee4fde9f1667bdfb1b1d577fcd3bcab48ad22aefc07a22e3f8ce0ee2323e
 size 8120