Hugging Face's logo

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

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

Commit History

Add Gemma-3-270m Taiwan
74c66e7
verified

Luigi commited on

add gemma-3-270m-it
3995aec

Luigi commited on

remove prevously added breeze models (as it didn't work), add smollm 135m taiwan
b3fd72e

Luigi commited on

add breeze models
88f3bc6

Luigi commited on

add 3 sub-1B TW models from ShengweiPeng
ddfffab

Luigi commited on

add Qwen2.5-Taiwan-3B-Reason-GRPO & Llama-3.2-Taiwan-1B
f82b9e0

Luigi commited on

disable cache for better compability
ea7c44f

Luigi commited on

make qwen2.5-taiwan 1.5b the default
493107e

Luigi commited on

add access_token to model loader
882aef2

Luigi commited on

add gemma 3n, smallthinker 4b0.6b and falcon h1-1.5b
de303d7

Luigi commited on

rename duckduckgo_search to ddgs
b858214

Luigi commited on

remove qwen3 30ba3b & 32b, but add 14b
e883ef3

Luigi commited on

use fp8 version of qwen3 30ba3b & 32b
9ece009

Luigi commited on

add qwe3 30ba3b awq & 30b awq
3a690c1

Luigi commited on

update prompt
8d42201

Luigi commited on

update prompt
5398786

Luigi commited on

fix err in prompt
b1fb4c7

Luigi commited on

improve prompt for better web search result merging
6a87eb4

Luigi commited on

Add D-R1-0528 8B, Nemotron 1.5B, Qwen2.5 Taiwan 1.5B
12d3fe3

Luigi commited on

reduce rep penality to 1.2
079e166

Luigi commited on

increase rep penality as on many slms, reptition is frequent.
8a7c97d

Luigi commited on

revert device_map to audo
cc12a51

Luigi commited on

Add smolLM2-135M GRPO and SmolLM2-360M
cb16ac6

Luigi commited on

add Qwen2.5-Omni-3B & MiMo-7B-RL
6a4537b

Luigi commited on

disable models unrunnable on hf spaces
7c5f318

Luigi commited on

switch Phi-4-mini-Instruct" from unsloth to microsoft
23b3848

Luigi commited on

extend max tokens
d730ffe

Luigi commited on

adjust layout
4911925

Luigi commited on

add "Granite-4.0-Tiny-Preview" model
09d9700

Luigi commited on

add phi-4 reasonning and phi-4-mini reasonning
68e6569

Luigi commited on

bugfix: set device to xpu by mistake
1242438

Luigi commited on

add all qwen3 variants
2882063

Luigi commited on

user can define search timeout
e2ee907

Luigi commited on

give 5 second for web earch to gather reults
c00d442

Luigi commited on

support thinking models and streamingly display thought
8c3c2b9

Luigi commited on

do not preview prompt at error return from chat response
c09049b

Luigi commited on

inject assistant placeholder at right time
12dd3f3

Luigi commited on

disable L142 which is not needed
3c176a1

Luigi commited on

fix bug in prompt preview display
41ee8bf

Luigi commited on

add prompt preview for debug
5fc0117

Luigi commited on

fix: prevent self-talking issue by using tokenizer chat_template formatting
960db60

Luigi commited on

bugfix to Error: "str" object has no attribute "pad_token_id"
889f080

Luigi commited on

add taiwan elm 1.1b & 270m instruct
c8399e3

Luigi commited on

add type in qwen3 0.6b repo id
76d4d60

Luigi commited on

add qwen3
fe395ab

Luigi commited on

Add Smollm2 360m instruct fine-tuned on TaiwanChat
7308211

Luigi commited on

keep debug message
37f7787

Luigi commited on

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