-
Notifications
You must be signed in to change notification settings - Fork 3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[llm]update peft docs #9655
[llm]update peft docs #9655
Conversation
Thanks for your contribution! |
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## develop #9655 +/- ##
===========================================
+ Coverage 52.21% 52.80% +0.58%
===========================================
Files 721 718 -3
Lines 114885 112225 -2660
===========================================
- Hits 59990 59259 -731
+ Misses 54895 52966 -1929 ☔ View full report in Codecov by Sentry. |
@@ -7,7 +7,7 @@ | |||
- 易用并行策略:支持纯数据并行(Data Parallelism)、分组参数切片的数据并行(Sharding Parallelism)、张量模型并行(Tensor Parallelism)、流水线模型并行(Pipeline Parallelism)、序列并行(Sequence parallelism)。 | |||
- 多种精度训练:16/32bit 全量精调、4/8/16bit LoRA 精调、混合量化 LoRA 精调。 | |||
- 性能极致优化:FlashAttention-2、FlashMask、Greedy Zero Padding。 | |||
- 先进精调策略:LoRA+、PiSSA、rsLoRA、NEFTune、VeRA。 | |||
- 先进精调策略:LoRA+、PiSSA、rsLoRA、NEFTune、VeRA、MoRA、ReFT、MoSLoRA。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
可以加上LoRA-GA,代码已经合入
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这块我看还没有开源模型适配示例,等 @greycooker 适配后由他加入吧
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
嗯嗯,这块我来加一下
@@ -150,7 +150,7 @@ python run_finetune.py ./config/llama/lora_argument.json | |||
python run_finetune.py ./config/llama/pt_argument.json | |||
``` | |||
|
|||
更多大模型精调分布式使用文档、训练细节和效果请参见[大模型精调教程](./docs/finetune.md)。 | |||
除了 LoRA、Prefix Tuning 外,还支持 LoKr、VeRA、MoRA、ReFT、rsLoRA、LoRA+、PiSSA、MoSLoRA 等多种精调算法,更多大模型精调使用文档、训练细节和效果请参见[大模型精调教程](./docs/finetune.md)。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LoRA-GA加上
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
PR types
Others
PR changes
Docs
Description
优化PEFT相关文档