make streaming response

apply history flatten before it goint to prompt

better management on system prompt

add accelerate

usue chat pipeline instead of model and tokenizer individually

bugfix to padding-related issues

add attention mask

Clean model description

pin torch to 2.4.0

add sentencepiece tokenzier

update requirements

enable zerogpu with decorator

Apply ZeroGPU

add apt.txt

adjust requirements

adjust requirements.txt

specify gpu build for llama cpp python

Update README.md

fix readme

switch to gradio version for stability reason

add taiwan tinyllama

Improve responsiveness by asynchronously retrieving web search context

update requirements

specify wheel of llama cpp python

openblas build of llam acpp filed

specify to build llama cpp with openblas

add llama 3.2 taiwan 3b

add minicpm3 4b

increase xt length to max

remove all moe

remove qwen 1.5 moe

adjust title style

use another version of qwen 1.5 moe

add Qwen1.5-MoE

Qwen2.5-MOE-6x1.5B

remove under 3b models

Add model caching

UI/UX Improvement

reset timeout timer once a new token is generated

open web search settgins to user

add 2 more models

apply new settings on duckduck search

tune llama paramters

increase max_chars_per_result to 600

increase max results to 6 for better web search

increase ctx lenght to 2k

increase timeout to 5min

Code simplification

Enable speculattive decoding

fix role disorder error in history