Downloads · 30 days
9
3% of all-time downloads
Llama3-70B-Orion-Chinese-SE
Orion-zhen/Llama3-70B-Orion-Chinese-SE
Llama3-70B-Orion-Chinese-SE is a text generation model from Orion-zhen. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.
本模型是从failspy/Llama-3-70B-Instruct-abliterated-v3经过DPO微调而来
All-time downloads
274
Public
Parameters
70.6B
141 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors141 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- llama3
- Model type
- llama
- Access
- Public
- Created
- Jun 5, 2024
- Updated
- Jun 5, 2024
- SHA
- 756fa576
Try a prompt
Model card
From the Hugging Face model README
Llama3-70B-Orion-Chinese-SE
概述
本模型是从failspy/Llama-3-70B-Instruct-abliterated-v3经过DPO微调而来
相较于Orion-zhen/Llama3-70B-Orion-Chinese, 本模型精简了DPO数据集, 力求对原模型影响最小的情况下获得较好的中文性能和emoji体验
本模型的emoji触发概率高于Orion-zhen/Llama3-70B-Orion-Chinese, 在其他方面稍逊于后者
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- llama3
- Languages
- en, zh
- Created
- Jun 5, 2024
- Updated
- Jun 5, 2024