Finetune Google Gemma model for Chinese Poem writing

Important! Gemma-IT format

GEMMA_IT_FORMAT = """<start_of_turn>user
{user_question}<end_of_turn>
<start_of_turn>model
"""

Before finetune using Gemma-it-7b

Before training
春风得意花铺路
春风得意花铺路,春暖花开,美不胜
美丽中国魅力北京
**美丽中国魅力北京,令人惊叹的现代与传统
鱼书千里梦
鱼书千里梦,是一个关于爱慕和成长的小说
日落晚霞临古寺
夕暮暮色,日落缓缓西下,将天空渲染成 Varies

After finetune (undertrained, after 10mins using T4 GPU, undertrained)

春风得意花铺路
秋雨流派诗作韵<eos>
美丽中国魅力北京
和谐社会和谐社会<eos>
鱼书千里梦
鸟歌百载歌<eos>
日落晚霞临古寺
月明清风送客船<eos>

Code to trigger this Lora ckpt (to be added)


Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.