Text Generation
Transformers
Safetensors
Chinese
English
qwen3
medical
conversational
Eval Results (legacy)
text-generation-inference
Instructions to use OpenMedZoo/MedGo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMedZoo/MedGo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OpenMedZoo/MedGo") 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("OpenMedZoo/MedGo") model = AutoModelForCausalLM.from_pretrained("OpenMedZoo/MedGo", 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]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use OpenMedZoo/MedGo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OpenMedZoo/MedGo" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenMedZoo/MedGo", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/OpenMedZoo/MedGo
- SGLang
How to use OpenMedZoo/MedGo 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 "OpenMedZoo/MedGo" \ --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": "OpenMedZoo/MedGo", "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 "OpenMedZoo/MedGo" \ --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": "OpenMedZoo/MedGo", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use OpenMedZoo/MedGo with Docker Model Runner:
docker model run hf.co/OpenMedZoo/MedGo
Update README_CN.md
Browse files- README_CN.md +4 -4
README_CN.md
CHANGED
|
@@ -27,7 +27,7 @@
|
|
| 27 |
|
| 28 |
## 🎯 简介
|
| 29 |
|
| 30 |
-
**MedGo** 是一个基于 **
|
| 31 |
|
| 32 |
### 🌟 核心能力
|
| 33 |
|
|
@@ -41,7 +41,7 @@
|
|
| 41 |
|
| 42 |
| 特性 | 详情 |
|
| 43 |
|------|------|
|
| 44 |
-
| **基础架构** |
|
| 45 |
| **参数规模** | 32B |
|
| 46 |
| **应用领域** | 临床医学、科研辅助、医疗系统集成 |
|
| 47 |
| **微调方法** | SFT + Preference Alignment (DPO/KTO) |
|
|
@@ -51,7 +51,7 @@
|
|
| 51 |
|
| 52 |
## 📊 性能评估
|
| 53 |
|
| 54 |
-
MedGo 在多项医学与综合评测基准上表现优异,在
|
| 55 |
|
| 56 |
### 主要基准测试结果
|
| 57 |
|
|
@@ -65,7 +65,7 @@ MedGo 在多项医学与综合评测基准上表现优异,在 30B 参数级别
|
|
| 65 |

|
| 66 |
|
| 67 |
**性能亮点**:
|
| 68 |
-
- ✅ **平均得分**: 约 70 分(
|
| 69 |
- ✅ **优势任务**: 临床推理(DiagnosisArena、CME)和多轮医学问答
|
| 70 |
- ✅ **平衡能力**: 在医疗语义理解和多任务泛化上表现良好
|
| 71 |
|
|
|
|
| 27 |
|
| 28 |
## 🎯 简介
|
| 29 |
|
| 30 |
+
**MedGo** 是一个基于 **Qwen3-32B** 微调的通用医疗大语言模型,专为临床医学与科研场景设计。模型通过大规模多源医学语料和复杂病例数据增强进行训练,支持医学问答、病历摘要、临床推理、多轮对话和科研文本生成等多任务能力。
|
| 31 |
|
| 32 |
### 🌟 核心能力
|
| 33 |
|
|
|
|
| 41 |
|
| 42 |
| 特性 | 详情 |
|
| 43 |
|------|------|
|
| 44 |
+
| **基础架构** | Qwen3-32B |
|
| 45 |
| **参数规模** | 32B |
|
| 46 |
| **应用领域** | 临床医学、科研辅助、医疗系统集成 |
|
| 47 |
| **微调方法** | SFT + Preference Alignment (DPO/KTO) |
|
|
|
|
| 51 |
|
| 52 |
## 📊 性能评估
|
| 53 |
|
| 54 |
+
MedGo 在多项医学与综合评测基准上表现优异,在 32B 参数级别模型中具有竞争力:
|
| 55 |
|
| 56 |
### 主要基准测试结果
|
| 57 |
|
|
|
|
| 65 |

|
| 66 |
|
| 67 |
**性能亮点**:
|
| 68 |
+
- ✅ **平均得分**: 约 70 分(32B 级别模型中表现优异)
|
| 69 |
- ✅ **优势任务**: 临床推理(DiagnosisArena、CME)和多轮医学问答
|
| 70 |
- ✅ **平衡能力**: 在医疗语义理解和多任务泛化上表现良好
|
| 71 |
|