---
title: Nous-Hermes-2-Mixtral-8x7B-DPO-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit.md"
repository: mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit
last_updated: 2024-12-20
license: apache-2.0
model_type:
  - mixtral
architectures:
  - MixtralForCausalLM
parameters: 7.5B
tensor_type:
  - F16
  - U32
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: 989
stars: 0
tags:
  - Mixtral
  - instruct
  - finetune
  - chatml
  - DPO
  - RLHF
  - gpt4
  - "synthetic data"
  - distillation
  - mlx
---

# Nous-Hermes-2-Mixtral-8x7B-DPO-4bit

> Nous-Hermes-2-Mixtral-8x7B-DPO-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit This model was converted to MLX format from NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO. Refer to the original model card for more…

mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit 是 ModelScope 魔搭社区上的 7.5B 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/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit
- **License**: apache-2.0
- **Parameters**: 7.5B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: Mixtral, instruct, finetune, chatml, DPO, RLHF, gpt4, synthetic data, distillation, mlx
- **Downloads**: 989
- **Stars**: 0
- **Last updated**: 2024-12-20

Source: https://www.modelscope.cn/models/mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit

---

# mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit
This model was converted to MLX format from [`NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO`]().
Refer to the [original model card](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO) 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/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
## Use with mlx_lm cli

```bash
pip install -U mlx-lm
python3 -m mlx_lm.generate --model mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit --prompt "<|im_start|>system\nYou are an accurate, educational, and helpful information assistant<|im_end|>\n<|im_start|>user\nWhat is the difference between awq vs gptq quantitization?<|im_end|>\n<|im_start|>assistant\n" --max-tokens 2048
```