---
title: CodeLlama-70b-Instruct-hf-4bit-MLX
canonical_url: "https://www.modelscope.cn/models/mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX"
md_url: "https://www.modelscope.cn/models/mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX.md"
repository: mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX
last_updated: 2024-12-20
license: llama2
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
parameters: 11.0B
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - code
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1000
stars: 1
tags:
  - llama-2
  - mlx
---

# CodeLlama-70b-Instruct-hf-4bit-MLX

> CodeLlama-70b-Instruct-hf-4bit-MLX - mlx-community 在 ModelScope 开源的模型。mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX This model was converted to MLX format from codellama/CodeLlama-70b-Instruct-hf. Refer to the original model card for more details on the…

mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX 是 ModelScope 魔搭社区上的 11.0B 参数text-generation模型，采用 llama2 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX
- **License**: llama2
- **Tasks**: text-generation
- **Parameters**: 11.0B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: llama-2, mlx
- **Downloads**: 1000
- **Stars**: 1
- **Last updated**: 2024-12-20

Source: https://www.modelscope.cn/models/mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX

---

![Alt text](https://cdn.discordapp.com/attachments/1064373193982361601/1201677160008384594/DALLE_2024-01-30_00.53.15_-_Imagine_a_whimsical_hyper-detailed_illustration_suitable_for_a_childrens_book_featuring_a_cartoon_alpaca_sitting_comfortably_and_using_an_Apple_lap.png?ex=65cab011&is=65b83b11&hm=373057e35079d276954594d43ea8e9e8223bd4956707a96c130a62850c8570b1&)

# mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX
This model was converted to MLX format from [`codellama/CodeLlama-70b-Instruct-hf`]().
Refer to the [original model card](https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf) for more details on the model.
## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX")
response = generate(model, tokenizer, prompt="<step>Source: user Fibonacci series in Python<step> Source: assistant Destination: user", verbose=True)
```