Instructions to use sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH with Transformers:

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

pipe = pipeline("text-generation", model="sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH")
model = AutoModelForCausalLM.from_pretrained("sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH

SGLang

How to use sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH 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 "sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH" \
    --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": "sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH",
		"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 "sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH" \
        --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": "sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH with Docker Model Runner:
```
docker model run hf.co/sunblaze-ucb/Qwen2.5-14B-Intuitor-MATH-1EPOCH
```

nielsr HF Staff commited on Mar 7

Commit

6dde306

verified ·

1 Parent(s): 5cb26dd

Improve model card: add library_name, paper/code links, and correct description

Browse files

Hi! I'm Niels, part of the community science team at Hugging Face.

This pull request improves your model card by:
- Adding `library_name: transformers` to the metadata to enable automated code snippets.
- Linking the model to its research paper: [Learning to Reason without External Rewards](https://huggingface.co/papers/2505.19590).
- Adding a link to the [official GitHub repository](https://github.com/sunblaze-ucb/Intuitor).
- Correcting a typo in the description (fixing the mention of 3B parameters to 14B).
- Providing a brief summary of the Intuitor method and RLIF paradigm.

Files changed (1) hide show

README.md +15 -9

README.md CHANGED Viewed

@@ -1,20 +1,27 @@
 ---
 base_model: Qwen/Qwen2.5-14B
-license: apache-2.0
 datasets:
-  - math
 metrics:
-  - accuracy
 pipeline_tag: text-generation
-language:
-  - en
 ---
 # Qwen2.5-14B-Intuitor-MATH-1EPOCH
-**Description:**
-An Intuitor-fine-tuned version of Qwen2.5-3B trained on the MATH dataset.
 ---
@@ -27,5 +34,4 @@ An Intuitor-fine-tuned version of Qwen2.5-3B trained on the MATH dataset.
   journal = {arXiv preprint arXiv:2505.19590},
   year    = {2025}
 }
-```

 ---
 base_model: Qwen/Qwen2.5-14B
 datasets:
+- math
+language:
+- en
+license: apache-2.0
 metrics:
+- accuracy
 pipeline_tag: text-generation
+library_name: transformers
 ---
 # Qwen2.5-14B-Intuitor-MATH-1EPOCH
+This model is an Intuitor-fine-tuned version of **Qwen2.5-14B** trained on the MATH dataset for one epoch.
+It was introduced in the paper [Learning to Reason without External Rewards](https://huggingface.co/papers/2505.19590). The official implementation is available in the [Intuitor GitHub repository](https://github.com/sunblaze-ucb/Intuitor).
+## Description
+**Intuitor** is a reinforcement learning method that fine-tunes large language models (LLMs) using *self-certainty*—the model’s own internal confidence—as the sole reward signal. It is built on a novel paradigm called **Reinforcement Learning from Internal Feedback (RLIF)**.
+RLIF enables LLMs to learn from intrinsic signals without external rewards, gold labels, or domain-specific verifiers. Intuitor replaces external rewards in Group Relative Policy Optimization (GRPO) with self-certainty scores, enabling fully unsupervised learning that generalizes well across different reasoning domains.
 ---
   journal = {arXiv preprint arXiv:2505.19590},
   year    = {2025}
 }
+```