Hugging Face's logo

Spaces:
Luigi
/
ZeroGPU-LLM-Inference
Running on Zero

App Files Community
ZeroGPU-LLM-Inference / app.py

Commit History

add minicpm3 4b
f5c0811

Luigi commited on

increase xt length to max
629495e

Luigi commited on

remove all moe
fafc8cb

Luigi commited on

remove qwen 1.5 moe
6735035

Luigi commited on

adjust title style
e9559bd

Luigi commited on

use another version of qwen 1.5 moe
96e60d6

Luigi commited on

add Qwen1.5-MoE
e17afaf

Luigi commited on

Qwen2.5-MOE-6x1.5B
5eca666

Luigi commited on

remove under 3b models
617be26

Luigi commited on

Add model caching
d33dfcd

Luigi commited on

UI/UX Improvement
eb215ff

Luigi commited on

reset timeout timer once a new token is generated
35943b1

Luigi commited on

open web search settgins to user
c9fd924

Luigi commited on

add 2 more models
f7a541f

Luigi commited on

apply new settings on duckduck search
d9421eb

Luigi commited on

tune llama paramters
20484f3

Luigi commited on

increase max_chars_per_result to 600
1155897

Luigi commited on

increase max results to 6 for better web search
0c2fe1d

Luigi commited on

increase ctx lenght to 2k
9ba47d1

Luigi commited on

increase timeout to 5min
71d28c5

Luigi commited on

Code simplification
248f5a7

Luigi commited on

Enable speculattive decoding
a7fdfe6

Luigi commited on

fix role disorder error in history
06a162a

Luigi commited on

Add internet search feature
4e60755

Luigi commited on

fix reasonning model's thought process display
9d3ca6c

Luigi commited on

bugfix
4522453

Luigi commited on

fix for multi-turn conv.
6c77ec7

Luigi commited on

bugfix for think tag handling
14564aa

Luigi commited on

support reasoning tag
5db22d5

Luigi commited on

add missing part of app.py
afa19a3

Luigi commited on

add 4 new models
d554072

Luigi commited on

fix error : ValueError: Conversation roles must alternate user/assistant/user/assistant
3e4847c

Luigi commited on

fault-free model loading
6e8312c

Luigi commited on

add storage indicator
cc91a1a

Luigi commited on

improve model management
0813164

Luigi commited on

improve storage management
37ee1f3

Luigi commited on

provide more models, secure memory usage
cd26609

Luigi commited on

increase context length to 2048
56919fd

Luigi commited on

switch to 7b model
ea7adad

Luigi commited on

switch to 3b q2 model
88b1f39

Luigi commited on

adjust thread numbers
4443d46

Luigi commited on

switch to 1.5b
4d633ef

Luigi commited on

fix model id
8287454

Luigi commited on

Add app.py & requirements.txt
0ff6c39

Luigi commited on