Instructions to use jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning with Transformers:

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

pipe = pipeline("text-generation", model="jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning")
model = AutoModelForMultimodalLM.from_pretrained("jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning")
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 jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning

SGLang

How to use jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning 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 "jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning" \
    --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": "jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning",
		"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 "jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning" \
        --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": "jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning with Docker Model Runner:
```
docker model run hf.co/jaygala24/Qwen2.5-3B-GRPO-KL-math-reasoning
```

jaygala24 commited on Apr 20

Commit

ebd5a33

verified ·

1 Parent(s): 7f1578f

Add pass@k evaluation results

Browse files

Files changed (1) hide show

README.md +12 -0

README.md CHANGED Viewed

@@ -59,6 +59,18 @@ Trained with [PipelineRL](https://github.com/ServiceNow/PipelineRL).
 | Precision | `bf16` |
 | DeepSpeed | ZeRO Stage 3 |
 ## Training Curves
 ![Training Metrics](training_metrics.png)

 | Precision | `bf16` |
 | DeepSpeed | ZeRO Stage 3 |
+## Evaluation Results
+Pass@k on math reasoning benchmarks (N=32 samples per problem, temperature=1.0):
+| Dataset | pass@1 | pass@2 | pass@4 | pass@8 | pass@16 | pass@32 |
+| --- | ---: | ---: | ---: | ---: | ---: | ---: |
+| GSM8K (test) | 85.60 | 90.73 | 93.78 | 95.74 | 97.08 | 97.95 |
+| MATH-500 | 65.11 | 73.19 | 79.51 | 84.60 | 88.55 | 91.40 |
+| **Overall** | **79.96** | **85.91** | **89.86** | **92.68** | **94.74** | **96.15** |
+*GSM8K test: 1319 problems · MATH-500: 500 problems · Overall: 1819 problems (overall weighted by problem count).*
 ## Training Curves
 ![Training Metrics](training_metrics.png)