---
license: apache-2.0
tags:
- llama3
- llama-factory
---

**RochatAI/llama3-8B-cn-rochat-v1** is an instruction-tuned language model from hfl/llama-3-chinese-8b-instruct-v3, focused on tunning for Chinese role-playing.

We perform supervised fine-tuning with our in-house high-quality instruction-following chat datasets. Afterwards, we do two rounds DPO training for some special cases. 

<img src="https://cdn-uploads.huggingface.co/production/uploads/64d8f3a9c3b41747a2a49e93/6wWKDRTc3kjGqc2lXNjqa.jpeg" alt="drawing" width="200"/>

## Contact Us

- Twitter/X: [Rochat_AI](https://x.com/Rochat_AI)
- Discord: [Rochat](https://discord.com/invite/BEfkByEJtD)

## Usage

### Recommend Samplers

```
temperature=0.98
top_p=0.37
top_k=100.0
repetition_penalty=1.18
```

### Prompt Template
 
Llama-3-Instruct:
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>
```

### Basic Roleplay System Prompt

```
Enter RP mode. You shall reply to {{user}} while staying in character. Write at least 1 paragraph, up to 3, no more than 300 words. Your responses must be detailed, creative, immersive, and drive the scenario forward. You will follow {{character}}'s persona and personality.
```