---
title: Dolphin-2.9.3-Mistral-Nemo-12b-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Dolphin-2.9.3-Mistral-Nemo-12b-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/Dolphin-2.9.3-Mistral-Nemo-12b-bf16.md"
repository: mlx-community/Dolphin-2.9.3-Mistral-Nemo-12b-bf16
last_updated: 2024-12-20
license: apache-2.0
model_type:
  - mistral
architectures:
  - MistralForCausalLM
parameters: 12.2B
tensor_type:
  - BF16
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: 986
stars: 0
tags:
  - generated_from_trainer
  - axolotl
  - mlx
---

# Dolphin-2.9.3-Mistral-Nemo-12b-bf16

> Dolphin-2.9.3-Mistral-Nemo-12b-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/Dolphin-2.9.3-mistral-nemo-12b-bf16

mlx-community/Dolphin-2.9.3-Mistral-Nemo-12b-bf16 是 ModelScope 魔搭社区上的 12.2B 参数机器学习模型，采用 apache-2.0 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/Dolphin-2.9.3-Mistral-Nemo-12b-bf16
- **License**: apache-2.0
- **Parameters**: 12.2B
- **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, axolotl, mlx
- **Downloads**: 986
- **Stars**: 0
- **Last updated**: 2024-12-20

Source: https://www.modelscope.cn/models/mlx-community/Dolphin-2.9.3-Mistral-Nemo-12b-bf16

---

# mlx-community/Dolphin-2.9.3-mistral-nemo-12b-bf16

The Model [mlx-community/Dolphin-2.9.3-mistral-nemo-12b-bf16](https://huggingface.co/mlx-community/Dolphin-2.9.3-mistral-nemo-12b-bf16) was converted to MLX format from [cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b](https://huggingface.co/cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b) using mlx-lm version **0.16.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Dolphin-2.9.3-mistral-nemo-12b-bf16")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```