---
title: Bio-Medical-Llama-3-8B
canonical_url: "https://www.modelscope.cn/models/mlx-community/Bio-Medical-Llama-3-8B"
md_url: "https://www.modelscope.cn/models/mlx-community/Bio-Medical-Llama-3-8B.md"
repository: mlx-community/Bio-Medical-Llama-3-8B
last_updated: 2025-02-07
license: other
model_type:
  - llama
architectures:
  - LlamaForCausalLM
parameters: 1.3B
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: 770
stars: 0
tags:
  - generated_from_trainer
  - medical
  - "Healthcare & Lifesciences"
  - BioMed
  - mlx
---

# Bio-Medical-Llama-3-8B

> Bio-Medical-Llama-3-8B - mlx-community 在 ModelScope 开源的模型。mlx-community/Bio-Medical-Llama-3-8B

mlx-community/Bio-Medical-Llama-3-8B 是 ModelScope 魔搭社区上的 1.3B 参数机器学习模型，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-Llama-3-8B
- **License**: other
- **Parameters**: 1.3B
- **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, mlx
- **Downloads**: 770
- **Stars**: 0
- **Last updated**: 2025-02-07

Source: https://www.modelscope.cn/models/mlx-community/Bio-Medical-Llama-3-8B

---

# mlx-community/Bio-Medical-Llama-3-8B

The Model [mlx-community/Bio-Medical-Llama-3-8B](https://huggingface.co/mlx-community/Bio-Medical-Llama-3-8B) was
converted to MLX format from [ContactDoctor/Bio-Medical-Llama-3-8B](https://huggingface.co/ContactDoctor/Bio-Medical-Llama-3-8B)
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-Llama-3-8B")

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)
```