GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
FreedomIntelligence
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
FreedomIntelligence
Model Tree
Qwen/Qwen3.8-27B
Input Modalities
Output Modalities
Supported Functionality
HuatuoGPT-3-27B is a medical LLM built on Qwen3.8-27B with One-stage Policy Optimization (OnePO). OnePO adapts language models to medicine in a single reinforcement-learning stage, without preceding domain-specific supervised fine-tuning. Teacher responses provide temporary guidance and are retired as the model improves.
We release the training code, medical RL dataset, and 8B rubric grader.
HuatuoGPT-3 requires thinking mode. Keep
enable_thinking=Trueduring inference. The model generates reasoning before providing its final answer after</think>.
| Model | Backbone | Purpose | Access |
|---|---|---|---|
| HuatuoGPT-3-9B | Qwen3.5-9B | Medical reasoning | HF Link |
| HuatuoGPT-3-27B | Qwen3.8-27B | Medical reasoning | HF Link |
HuatuoGPT-3-27B can be used like Qwen3.8-27B and deployed with vLLM or SGLang.
For direct text inference, use a Transformers version with Qwen3.5 support (transformers>=5.4.0) and accelerate:
python
from transformers import AutoModelForImageTextToText, AutoProcessor model_id = "FreedomIntelligence/HuatuoGPT-3-27B"processor = AutoProcessor.from_pretrained(model_id)model = AutoModelForImageTextToText.from_pretrained( model_id, dtype="auto", device_map="auto",).eval() messages = [{ "role": "user", "content": [{"type": "text", "text": "What are the common causes of chest pain?"}],}]inputs = processor.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, enable_thinking=True, return_dict=True, return_tensors="pt",).to(model.device) outputs = model.generate(**inputs, max_new_tokens=4096)response = outputs[0, inputs["input_ids"].shape[-1]:]print(processor.decode(response, skip_special_tokens=True))bibtex
@inproceedings{chen2026onepo, title={OnePO: Direct One-stage Policy Optimization for SFT-free Domain Adaptation}, author={Chen, Junying and Xie, Xinyuan and Li, Ziniu and Wang, Benyou}, booktitle={Proceedings of the 43rd International Conference on Machine Learning}, year={2026}}from transformers import AutoModelForImageTextToText, AutoProcessor model_id = "FreedomIntelligence/HuatuoGPT-3-27B"processor = AutoProcessor.from_pretrained(model_id)model = AutoModelForImageTextToText.from_pretrained( model_id, dtype="auto", device_map="auto",).eval() messages = [{ "role": "user", "content": [{"type": "text", "text": "What are the common causes of chest pain?"}],}]inputs = processor.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, enable_thinking=True, return_dict=True, return_tensors="pt",).to(model.device) outputs = model.generate(**inputs, max_new_tokens=4096)response = outputs[0, inputs["input_ids"].shape[-1]:]print(processor.decode(response, skip_special_tokens=True))@inproceedings{chen2026onepo, title={OnePO: Direct One-stage Policy Optimization for SFT-free Domain Adaptation}, author={Chen, Junying and Xie, Xinyuan and Li, Ziniu and Wang, Benyou}, booktitle={Proceedings of the 43rd International Conference on Machine Learning}, year={2026}}