---
title: dolphin-2.2-70b-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/dolphin-2.2-70b-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/dolphin-2.2-70b-8bit.md"
repository: mlx-community/dolphin-2.2-70b-8bit
last_updated: 2024-12-20
license: llama2
model_type:
  - llama
architectures:
  - LlamaForCausalLM
parameters: 21.7B
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 974
stars: 0
tags:
  - mlx
---

# dolphin-2.2-70b-8bit

> dolphin-2.2-70b-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/dolphin-2.2-70b-8bit This model was converted to MLX format from cognitivecomputations/dolphin-2.2-70b using mlx-lm version 0.7.0. Refer to the original model card for more details on the…

mlx-community/dolphin-2.2-70b-8bit 是 ModelScope 魔搭社区上的 21.7B 参数机器学习模型，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/dolphin-2.2-70b-8bit
- **License**: llama2
- **Parameters**: 21.7B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 974
- **Stars**: 0
- **Last updated**: 2024-12-20

Source: https://www.modelscope.cn/models/mlx-community/dolphin-2.2-70b-8bit

---

# mlx-community/dolphin-2.2-70b-8bit
This model was converted to MLX format from [`cognitivecomputations/dolphin-2.2-70b`]() using mlx-lm version **0.7.0**.
Refer to the [original model card](https://huggingface.co/cognitivecomputations/dolphin-2.2-70b) 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/dolphin-2.2-70b-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```