Hugging Face's logo

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

App Files Community
ZeroGPU-LLM-Inference

Commit History

add debug to show web resarch result
a2f07a4

Luigi commited on

give 1 second for web search to grab data
9ad3ffd

Luigi commited on

inject web search result if web search enabled
bc257ff

Luigi commited on

refactor(app): improve streaming, background search, dtype fallback, and cleanup :contentReference[oaicite:0]{index=0}
293686e

Luigi commited on

bugfixc: not using pipeline for response generation
939895d

Luigi commited on

Add original SmolLM2 135M Instruct for comparaison
423dc1a

Luigi commited on

Add SmolLM2-135M-Instruct-TaiwanChat
38fcc03

Luigi commited on

Add SmolLM2-135M TaiwanChat
0d642b7

Luigi commited on

Update README.md
34cf84a
verified

Luigi commited on

default to gemma-3-4b
88a6a62

Luigi commited on

model repo_id typo fix
89372fa

Luigi commited on

enable web search by default
6235e63

Luigi commited on

remove tinyllama which has bad response quality
a22cf42

Luigi commited on

make streaming response
5ea073d

Luigi commited on

apply history flatten before it goint to prompt
ef361b0

Luigi commited on

better management on system prompt
5f6306a

Luigi commited on

add accelerate
5ed3cb3

Luigi commited on

usue chat pipeline instead of model and tokenizer individually
ac8e9cc

Luigi commited on

bugfix to padding-related issues
f248fec

Luigi commited on

add attention mask
b6b3940

Luigi commited on

Clean model description
4731160

Luigi commited on

pin torch to 2.4.0
4c6b4c5

Luigi commited on

add sentencepiece tokenzier
4afc958

Luigi commited on

update requirements
51e3e3c

Luigi commited on

enable zerogpu with decorator
c5b2897

Luigi commited on

Apply ZeroGPU
d181b45

Luigi commited on

add apt.txt
5dd835a

Luigi commited on

adjust requirements
e85692d

Luigi commited on

adjust requirements.txt
931fd49

Luigi commited on

specify gpu build for llama cpp python
49a4dad

Luigi commited on

Update README.md
d6f7cc4
verified

Luigi commited on

fix readme
c62b652

Luigi commited on

switch to gradio version for stability reason
a703203

Luigi commited on

add taiwan tinyllama
794ee70

Luigi commited on

Improve responsiveness by asynchronously retrieving web search context
acda3f1

Luigi commited on

update requirements
12731c2

Luigi commited on

specify wheel of llama cpp python
f200cb7

Luigi commited on

openblas build of llam acpp filed
66a3cb6

Luigi commited on

specify to build llama cpp with openblas
e883a1b

Luigi commited on

add llama 3.2 taiwan 3b
b1544e2

Luigi commited on

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