fireballoon
/

baichuan-vicuna-chinese-7b

Text Generation

text-generation-inference

Model card Files Files and versions

Resources

View closed (8)

Adding `safetensors` variant of this model

#17 opened 10 months ago by

Adding Evaluation Results

#15 opened over 2 years ago by

leaderboard-pr-bot

请问deepspeed zero3的参数是怎么配置的

#14 opened over 2 years ago by

loss震荡幅度比较大是正常的嘛，loss是在3个epoch的哪个时候开始下降并保持稳定的呢

#13 opened over 2 years ago by

请问eval data 应该如何获取

#11 opened over 2 years ago by

继续微调的问题

#9 opened over 2 years ago by

模型效果超出预期，很棒！！

#8 opened over 2 years ago by

请问这个sft用到了哪些数据，总共是多少量级？

#7 opened over 2 years ago by

Why you have the most py files in the configfile ?

#3 opened over 2 years ago by