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

Add internet search feature

fix reasonning model's thought process display

bugfix

fix for multi-turn conv.

bugfix for think tag handling

support reasoning tag

add missing part of app.py

add 4 new models

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

fault-free model loading

add storage indicator

improve model management

improve storage management

provide more models, secure memory usage

increase context length to 2048

switch to 7b model

switch to 3b q2 model

adjust thread numbers

switch to 1.5b

fix model id

Add app.py & requirements.txt