Instructions to use IFM/guru-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IFM/guru-32B with Transformers:

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

pipe = pipeline("text-generation", model="IFM/guru-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("IFM/guru-32B")
model = AutoModelForCausalLM.from_pretrained("IFM/guru-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 IFM/guru-32B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/IFM/guru-32B

SGLang

How to use IFM/guru-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 "IFM/guru-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": "IFM/guru-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 "IFM/guru-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": "IFM/guru-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IFM/guru-32B with Docker Model Runner:
```
docker model run hf.co/IFM/guru-32B
```

nielsr HF Staff commited on Jun 20, 2025

Commit

09e2f10

verified ·

1 Parent(s): 21de8c1

Add project page URL

Browse files

This PR adds the project page URL to the model card.

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-pipeline_tag: text-generation
 license: cc-by-nc-4.0
 ---
 This repository contains the Guru-32B (base Qwen2.5-32B) model presented in [Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective](https://huggingface.co/papers/2506.14965).
@@ -29,7 +29,7 @@ The leaderboard is evaluated with our evaluation [code](https://github.com/LLM36
 |                | LiveBench                     |       18.57 |                   19.76  |       12.64 |          15.20 |        34.30 |         28.78 |            28.33 |
 |                | **Average Score**              | **43.29**   | **33.76**               | **35.42**   | **33.97**      | **54.24**    | **47.53**     | **46.25**        |
 Example usage:
 ```python
@@ -45,4 +45,4 @@ outputs = model.generate(prompt, max_new_tokens=256, temperature=1.0, top_p=0.7)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
-Please refer to the [paper](https://arxiv.org/abs/2506.14965) for more details.

 ---
 library_name: transformers
 license: cc-by-nc-4.0
+pipeline_tag: text-generation
 ---
 This repository contains the Guru-32B (base Qwen2.5-32B) model presented in [Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective](https://huggingface.co/papers/2506.14965).
 |                | LiveBench                     |       18.57 |                   19.76  |       12.64 |          15.20 |        34.30 |         28.78 |            28.33 |
 |                | **Average Score**              | **43.29**   | **33.76**               | **35.42**   | **33.97**      | **54.24**    | **47.53**     | **46.25**        |
+Project page: [Project page URL]
 Example usage:
 ```python
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
+Please refer to the [paper](https://arxiv.org/abs/2506.14965) for more details.