---
title: Athene-V2-Chat-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Athene-V2-Chat-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Athene-V2-Chat-8bit.md"
repository: mlx-community/Athene-V2-Chat-8bit
last_updated: 2024-12-19
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - Nexusflow/Athene-V2-Chat
base_model_relation: quantized
parameters: 20.5B
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: 1041
stars: 0
tags:
  - RLHF
  - Nexusflow
  - Athene
  - "Chat Model"
  - mlx
  - mlx-my-repo
---

# Athene-V2-Chat-8bit

> Athene-V2-Chat-8bit - mlx-community 在 ModelScope 开源的模型。The Model mlx-community/Athene-V2-Chat-8bit was converted to MLX format from Nexusflow/Athene-V2-Chat using mlx-lm version 0.19.2.

mlx-community/Athene-V2-Chat-8bit 是 ModelScope 魔搭社区上的 20.5B 参数text-generation模型，采用 other 许可，基于 Nexusflow/Athene-V2-Chat 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/Athene-V2-Chat-8bit
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 20.5B
- **Base model**: Nexusflow/Athene-V2-Chat
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: RLHF, Nexusflow, Athene, Chat Model, mlx, mlx-my-repo
- **Downloads**: 1041
- **Stars**: 0
- **Last updated**: 2024-12-19

Source: https://www.modelscope.cn/models/mlx-community/Athene-V2-Chat-8bit

---

# Athene-V2-Chat-8bit

The Model [mlx-community/Athene-V2-Chat-8bit](https://huggingface.co/mlx-community/Athene-V2-Chat-8bit) was converted to MLX format from [Nexusflow/Athene-V2-Chat](https://huggingface.co/Nexusflow/Athene-V2-Chat) using mlx-lm version **0.19.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Athene-V2-Chat-8bit")

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)
```