release v1.7.4
This commit is contained in:
parent
4bed070556
commit
e625e1f783
@ -2,24 +2,15 @@
|
|||||||
|
|
||||||
### Features
|
### Features
|
||||||
|
|
||||||
- add Docker support (#291) @LonghronShen
|
- rwkv6 lora finetune support (https://github.com/JL-er/RWKV-LORA)
|
||||||
|
- latex support
|
||||||
### Fixes
|
|
||||||
|
|
||||||
- fix a generation exception caused by potentially dangerous regex being passed into the stop array
|
|
||||||
- fix max_tokens parameter of Chat page not being passed to backend
|
|
||||||
- fix the issue where penalty_decay and global_penalty are not being passed to the backend default config when running
|
|
||||||
the model through client
|
|
||||||
|
|
||||||
### Improvements
|
### Improvements
|
||||||
|
|
||||||
- prevent 'torch' has no attribute 'cuda' error in torch_gc, so user can use CPU or WebGPU (#302)
|
- improve markdown rendering
|
||||||
|
- improve theme
|
||||||
### Chores
|
- improve usability
|
||||||
|
- for Chinese users, replace Tsinghua pip mirrors with Alibaba Cloud to avoid 403 http error
|
||||||
- bump dependencies
|
|
||||||
- add pre-release workflow
|
|
||||||
- dep_check.py now ignores GPUtil
|
|
||||||
|
|
||||||
## Install
|
## Install
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user