Instructions to use TianHongZXY/CHIMERA-4B-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TianHongZXY/CHIMERA-4B-RL with Transformers:

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

pipe = pipeline("text-generation", model="TianHongZXY/CHIMERA-4B-RL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TianHongZXY/CHIMERA-4B-RL")
model = AutoModelForCausalLM.from_pretrained("TianHongZXY/CHIMERA-4B-RL", 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 TianHongZXY/CHIMERA-4B-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TianHongZXY/CHIMERA-4B-RL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TianHongZXY/CHIMERA-4B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TianHongZXY/CHIMERA-4B-RL

SGLang

How to use TianHongZXY/CHIMERA-4B-RL 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 "TianHongZXY/CHIMERA-4B-RL" \
    --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": "TianHongZXY/CHIMERA-4B-RL",
		"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 "TianHongZXY/CHIMERA-4B-RL" \
        --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": "TianHongZXY/CHIMERA-4B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TianHongZXY/CHIMERA-4B-RL with Docker Model Runner:
```
docker model run hf.co/TianHongZXY/CHIMERA-4B-RL
```

nielsr HF Staff commited on Mar 8

Commit

475f937

verified ·

1 Parent(s): 921fcd3

Add paper link and model metadata

Browse files

Hi! I'm Niels from the Hugging Face community science team. This pull request improves the model card by:
- Adding the `pipeline_tag: text-generation` to improve discoverability.
- Specifying `library_name: transformers` based on the configuration files.
- Linking the model to the official research paper: [CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning](https://huggingface.co/papers/2603.00889).
- Adding author attribution and a citation section.

Files changed (1) hide show

README.md +25 -2

README.md CHANGED Viewed

@@ -1,14 +1,27 @@
 ---
-datasets:
-- TianHongZXY/CHIMERA
 base_model:
 - Qwen/Qwen3-4B-Thinking-2507
 ---
 # CHIMERA-4B-RL
 CHIMERA-4B-RL is [CHIMERA-4B-SFT](https://huggingface.co/TianHongZXY/CHIMERA-4B-SFT) further trained with reinforcement learning on the [CHIMERA](https://huggingface.co/datasets/TianHongZXY/CHIMERA) dataset.
 ## Results
 | Model | GPQA-D | AIME 24 | AIME 25 | AIME 26 | HMMT Feb 25 | HMMT Nov 25 | HLE |
@@ -16,3 +29,13 @@ CHIMERA-4B-RL is [CHIMERA-4B-SFT](https://huggingface.co/TianHongZXY/CHIMERA-4B-
 | Qwen3-4B-Thinking-2507 | 65.8 | 81.6 | **81.0** | 80.8 | 59.2 | 57.3 | 7.3 |
 | CHIMERA-4B-SFT | 68.8 | 86.5 | 79.8 | 80.3 | 63.1 | 66.3 | **9.0** |
 | **CHIMERA-4B-RL** | **70.1** | **86.9** | 80.7 | **82.7** | **65.7** | **67.0** | **9.0** |

 ---
 base_model:
 - Qwen/Qwen3-4B-Thinking-2507
+datasets:
+- TianHongZXY/CHIMERA
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- reasoning
+- synthetic-data
+- chain-of-thought
 ---
 # CHIMERA-4B-RL
+This model was introduced in the paper [CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning](https://huggingface.co/papers/2603.00889).
+**Authors:** Xinyu Zhu, Yihao Feng, Yanchao Sun, Xianzhi Du, Pingzhi Li, Olli Saarikivi, Yun Zhu, Yu Meng.
+## Description
 CHIMERA-4B-RL is [CHIMERA-4B-SFT](https://huggingface.co/TianHongZXY/CHIMERA-4B-SFT) further trained with reinforcement learning on the [CHIMERA](https://huggingface.co/datasets/TianHongZXY/CHIMERA) dataset.
+CHIMERA is a compact synthetic reasoning dataset comprising 9K samples designed for generalizable cross-domain reasoning. It provides rich, long Chain-of-Thought (CoT) trajectories across 8 major scientific disciplines. Despite its modest size, post-training a 4B model on this data allows it to approach or match the reasoning performance of significantly larger models like DeepSeek-R1 and Qwen3-235B.
 ## Results
 | Model | GPQA-D | AIME 24 | AIME 25 | AIME 26 | HMMT Feb 25 | HMMT Nov 25 | HLE |
 | Qwen3-4B-Thinking-2507 | 65.8 | 81.6 | **81.0** | 80.8 | 59.2 | 57.3 | 7.3 |
 | CHIMERA-4B-SFT | 68.8 | 86.5 | 79.8 | 80.3 | 63.1 | 66.3 | **9.0** |
 | **CHIMERA-4B-RL** | **70.1** | **86.9** | 80.7 | **82.7** | **65.7** | **67.0** | **9.0** |
+## Citation
+```bibtex
+@article{zhu2026chimera,
+  title={CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning},
+  author={Zhu, Xinyu and Feng, Yihao and Sun, Yanchao and Du, Xianzhi and Li, Pingzhi and Saarikivi, Olli and Zhu, Yun and Meng, Yu},
+  journal={arXiv preprint arXiv:2603.00889},
+  year={2026}
+}
+```