Spaces:
Running
Running
Commit History
-
add Qwen1.5-MoE
e17afaf -
Qwen2.5-MOE-6x1.5B
5eca666 -
remove under 3b models
617be26 -
Add model caching
d33dfcd -
UI/UX Improvement
eb215ff -
reset timeout timer once a new token is generated
35943b1
-
open web search settgins to user
c9fd924 -
add 2 more models
f7a541f -
apply new settings on duckduck search
d9421eb -
tune llama paramters
20484f3 -
increase max_chars_per_result to 600
1155897 -
increase max results to 6 for better web search
0c2fe1d -
increase ctx lenght to 2k
9ba47d1 -
increase timeout to 5min
71d28c5 -
Code simplification
248f5a7 -
Enable speculattive decoding
a7fdfe6 -
fix role disorder error in history
06a162a -
Add internet search feature
4e60755 -
fix reasonning model's thought process display
9d3ca6c -
bugfix
4522453 -
fix for multi-turn conv.
6c77ec7 -
bugfix for think tag handling
14564aa -
support reasoning tag
5db22d5 -
add missing part of app.py
afa19a3 -
fix readme error due to short description length
1bd76fd -
add 4 new models
d554072 -
fix error : ValueError: Conversation roles must alternate user/assistant/user/assistant
3e4847c -
upgrade llamacpp version
b6129d9 -
fault-free model loading
6e8312c -
add storage indicator
cc91a1a -
improve model management
0813164 -
improve storage management
37ee1f3 -
fix yaml error
3190ad6 -
provide more models, secure memory usage
cd26609 -
increase context length to 2048
56919fd -
update readme for 7b
f746942 -
switch to 7b model
ea7adad
-
switch to 3b q2 model
88b1f39 -
Update README.md
Verified signatureb5ee7db -
adjust thread numbers
4443d46 -
switch to 1.5b
4d633ef -
fix model id
8287454 -
Add app.py & requirements.txt
0ff6c39 -
initial commit
Verified signatureef1afaf
