对比Baichuan7B #36
Replies: 12 comments 1 reply
-
@GXYM 你用的是哪个模型?明显模型不对,或者用法有误。你这个截图的输出基本就是胡说八道的情况了。 |
Beta Was this translation helpful? Give feedback.
-
模型下载对的,我用了别的gradio启动脚本,等我换成官方的gradio启动脚本在测测 |
Beta Was this translation helpful? Give feedback.
-
用的是这个模型[ziqingyang/chinese-llama-2-7b]看来就是模型很拉跨,不是我用了那个脚本导致的, 和百川没法比 |
Beta Was this translation helpful? Give feedback.
-
@GXYM 你指向的模型是LLaMA-2啊 😅 我们的指令模型是Alpaca-2。 |
Beta Was this translation helpful? Give feedback.
-
那我在测测ziqingyang/chinese-llama-2-7b |
Beta Was this translation helpful? Give feedback.
-
我觉得你应该测的是ziqingyang/chinese-alpaca-2-7b |
Beta Was this translation helpful? Give feedback.
-
但是chinese-alpaca-2-7b才是指令模型..是指你应该去测那个 |
Beta Was this translation helpful? Give feedback.
-
哦哦,那我再去测测那个指令模型 |
Beta Was this translation helpful? Give feedback.
-
|
Beta Was this translation helpful? Give feedback.
-
和百川比怎么样? 我也是准备测一下 |
Beta Was this translation helpful? Give feedback.
-
chinese-alpaca-2-7b: |
Beta Was this translation helpful? Give feedback.
-
@GXYM 咱也不知道你是怎么用的,比如你写的
我建议是先评测模型使用的正确性,再进行效果对比。 目录中的examples目录里有示例输出,如果你得不到类似的输出说明某些环节存在问题。 考虑到以上已经不属于Issue类问题,如有问题请发在讨论区(已转移本thread)。 |
Beta Was this translation helpful? Give feedback.
-
提交前必须检查以下项目
问题类型
效果问题
基础模型
LLaMA-2-7B
操作系统
None
详细描述问题
可否对比一下Baichuan7B,看看相较于Baichuan,各方面差异如何
依赖情况(代码类问题务必提供)
运行日志或截图
Beta Was this translation helpful? Give feedback.
All reactions