Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Instructions to use bruel/Qwen2.5-1.5B-Open-R1-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bruel/Qwen2.5-1.5B-Open-R1-GRPO with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bruel/Qwen2.5-1.5B-Open-R1-GRPO") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bruel/Qwen2.5-1.5B-Open-R1-GRPO") model = AutoModelForCausalLM.from_pretrained("bruel/Qwen2.5-1.5B-Open-R1-GRPO", 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 bruel/Qwen2.5-1.5B-Open-R1-GRPO with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bruel/Qwen2.5-1.5B-Open-R1-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": "bruel/Qwen2.5-1.5B-Open-R1-GRPO", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/bruel/Qwen2.5-1.5B-Open-R1-GRPO
- SGLang
How to use bruel/Qwen2.5-1.5B-Open-R1-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 "bruel/Qwen2.5-1.5B-Open-R1-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": "bruel/Qwen2.5-1.5B-Open-R1-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 "bruel/Qwen2.5-1.5B-Open-R1-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": "bruel/Qwen2.5-1.5B-Open-R1-GRPO", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use bruel/Qwen2.5-1.5B-Open-R1-GRPO with Docker Model Runner:
docker model run hf.co/bruel/Qwen2.5-1.5B-Open-R1-GRPO
Download training_args.bin from bruel/Qwen2.5-1.5B-Open-R1-GRPO: direct link, hf CLI and curl.
- Browser
- Download file 7.48 kB
-
https://huggingface.co/bruel/Qwen2.5-1.5B-Open-R1-GRPO/resolve/main/training_args.bin
- Command line
-
hf download hf://bruel/Qwen2.5-1.5B-Open-R1-GRPO/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/bruel/Qwen2.5-1.5B-Open-R1-GRPO/resolve/main/training_args.bin
7.48 kB
- Xet hash:
- 5d1a65ade0e799a31639bff6502889dfe3433d0f619f68ccced652f05ee5511b
- Size of remote file:
- 7.48 kB
- SHA256:
- e81028790fb3d3f5d6f376245c71297fed6ab72454aa24b3f36c69f7bc9ce2d8
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.