Llama3 8B Cn Rochat V1

🚀 RochatAI/llama3-8B-cn-rochat-v1

An instruction-tuned language model based on hfl/llama-3-chinese-8b-instruct-v3, optimized for Chinese role-playing.

RochatAI/llama3-8B-cn-rochat-v1 is an instruction-tuned language model derived from hfl/llama-3-chinese-8b-instruct-v3. It is specifically tuned for Chinese role-playing scenarios.

We conducted supervised fine-tuning using our in - house high - quality instruction - following chat datasets. Subsequently, we performed two rounds of DPO training for certain special cases.

📄 License

The model is licensed under the Apache 2.0 license.

📞 Contact Us

• Twitter/X: Rochat_AI
• Discord: Rochat

💻 Usage Examples

🛠️ 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.