File tree 2 files changed +5
-7
lines changed
2 files changed +5
-7
lines changed Original file line number Diff line number Diff line change 1
- ## v2.1.2
1
+ ## v2.2.0
2
2
#### 🚀 Features
3
3
4
- - Update to latest llama.cpp (b3617) (PR: #210 )
5
- - Integrate Llama 3.1 and Gemma2 models in model dropdown
6
4
- Implement embedding and lora adapter functionality (PR: #210 )
7
5
- Read context length and warn if it is very large (PR: #211 )
8
- - Setup to allow to use extra features: flash attention and IQ quants (PR: #216 )
6
+ - Setup allowing to use extra features: flash attention and IQ quants (PR: #216 )
9
7
- Allow HTTP request retries for remote server (PR: #217 )
10
8
- Allow to set lora weights at startup, add unit test (PR: #219 )
9
+ - allow relative StreamingAssets paths for models (PR: #221 )
11
10
12
11
#### 🐛 Fixes
13
12
Original file line number Diff line number Diff line change 1
1
### 🚀 Features
2
2
3
- - Update to latest llama.cpp (b3617) (PR: #210 )
4
- - Integrate Llama 3.1 and Gemma2 models in model dropdown
5
3
- Implement embedding and lora adapter functionality (PR: #210 )
6
4
- Read context length and warn if it is very large (PR: #211 )
7
- - Setup to allow to use extra features: flash attention and IQ quants (PR: #216 )
5
+ - Setup allowing to use extra features: flash attention and IQ quants (PR: #216 )
8
6
- Allow HTTP request retries for remote server (PR: #217 )
9
7
- Allow to set lora weights at startup, add unit test (PR: #219 )
8
+ - allow relative StreamingAssets paths for models (PR: #221 )
10
9
11
10
### 🐛 Fixes
12
11
You can’t perform that action at this time.
0 commit comments