Instructions to use Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat with Transformers:

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

pipe = pipeline("text-generation", model="Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat")
model = AutoModelForCausalLM.from_pretrained("Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat")
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 Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat

SGLang

How to use Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat 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 "Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat" \
    --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": "Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat",
		"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 "Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat" \
        --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": "Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat with Docker Model Runner:
```
docker model run hf.co/Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-noformat
```

Lansechen commited on Apr 3, 2025

Commit

0ab9538

verified ·

1 Parent(s): ab08930

Training in progress, epoch 1

Browse files

Files changed (4) hide show

model-00001-of-00004.safetensors +1 -1
model-00002-of-00004.safetensors +1 -1
model-00003-of-00004.safetensors +1 -1
model-00004-of-00004.safetensors +1 -1

model-00001-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1a72902788e158785376ad3e9b264b516f1ac11458b62c5e1af0870e6f8c566
 size 4877660776

 version https://git-lfs.github.com/spec/v1
+oid sha256:a0d4464d5c6a2f41ae26cdca8f7083ca3cb57b7f470e0b912cf51dd39fd36530
 size 4877660776

model-00002-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b22a1077360ecc1ae3860c9911b2f9eaa5ac35a2b825e128b6fcc563950a03b1
 size 4932751008

 version https://git-lfs.github.com/spec/v1
+oid sha256:49a36fc09c5b8b604bcc7d3520d789bd992664f64b5ec5a042239f7e2b25c857
 size 4932751008

model-00003-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5918a570db45fb6324ff6fd3d4a2a1f44bc445bcb6b54033b3ed74a60eb68bb3
 size 4330865200

 version https://git-lfs.github.com/spec/v1
+oid sha256:ceb96f1940ba5d0464b176dee905a5ceb65eeacdb7c8664c136f5c18c9fb3076
 size 4330865200

model-00004-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b6475c09d1061106c4a287972b5d864b41dcc43ba1ffee6d48f59c86d71612b
 size 1089994880

 version https://git-lfs.github.com/spec/v1
+oid sha256:b5a659229c419b657f9519b5438898fb84b0a9384aacd73b77ad81d6acb6fc9c
 size 1089994880