---
title: Bio-Medical-3B-CoT-012025
canonical_url: "https://www.modelscope.cn/models/mlx-community/Bio-Medical-3B-CoT-012025"
md_url: "https://www.modelscope.cn/models/mlx-community/Bio-Medical-3B-CoT-012025.md"
repository: mlx-community/Bio-Medical-3B-CoT-012025
last_updated: 2025-01-27
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
parameters: 482.3M
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 2472
stars: 0
tags:
  - generated_from_trainer
  - medical
  - "Healthcare & Lifesciences"
  - BioMed
  - chain-of-thought
  - mlx
---

# Bio-Medical-3B-CoT-012025

> Bio-Medical-3B-CoT-012025 - mlx-community 在 ModelScope 开源的模型。mlx-community/Bio-Medical-3B-CoT-012025

mlx-community/Bio-Medical-3B-CoT-012025 是 ModelScope 魔搭社区上的 482.3M 参数text-generation模型，采用 other 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/Bio-Medical-3B-CoT-012025
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 482.3M
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: generated_from_trainer, medical, Healthcare & Lifesciences, BioMed, chain-of-thought, mlx
- **Downloads**: 2472
- **Stars**: 0
- **Last updated**: 2025-01-27

Source: https://www.modelscope.cn/models/mlx-community/Bio-Medical-3B-CoT-012025

---

# mlx-community/Bio-Medical-3B-CoT-012025

The Model [mlx-community/Bio-Medical-3B-CoT-012025](https://huggingface.co/mlx-community/Bio-Medical-3B-CoT-012025) was
converted to MLX format from [ContactDoctor/Bio-Medical-3B-CoT-012025](https://huggingface.co/ContactDoctor/Bio-Medical-3B-CoT-012025)
using mlx-lm version **0.20.1**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Bio-Medical-3B-CoT-012025")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```