This website requires JavaScript.
b309ef2c0e
More modifications
master
Samuele Lorefice
2025-01-23 16:11:18 +01:00
ac63019fe6
Adds history command
Samuele Lorefice
2024-12-27 18:00:58 +01:00
773203127f
They can now answer
Samuele Lorefice
2024-12-26 20:19:59 +01:00
124a4c66fe
Adds correct command check
Samuele Lorefice
2024-12-26 19:51:17 +01:00
e90e0200e1
Removes ratelimit, refactors everything in more sections, adds tokenization calculation
Samuele Lorefice
2024-12-26 19:47:07 +01:00
000b32c41d
Last work before refactor
Samuele Lorefice
2024-12-26 17:26:29 +01:00
0fe19ce04f
Added speaker hinting
Samuele Lorefice
2024-12-26 16:51:18 +01:00
50e5ea6533
Implemented ratelimit
Samuele Lorefice
2024-12-26 16:51:03 +01:00
54691774e2
Renamed tg bot container to telegrambot, moved prompt file to bot subproject
Samuele Lorefice
2024-12-26 16:31:06 +01:00
454dbb7e2a
Added GetEnv shorthand, moved Prompt loading to external file
Samuele Lorefice
2024-12-26 16:22:56 +01:00
65950e3642
Solves context out of bound due to history
Samuele Lorefice
2024-12-26 04:32:11 +01:00
4167c75279
Added rop of pending updates on bot start, reset command, AnswerChat method, GPU offload, limit to response lenght, context reduced to 2048, flash attention, 4 parallel decode queues, --keep of the original 810 tokens (which is the starting prompt)
Samuele Lorefice
2024-12-26 03:24:56 +01:00
296d150282
Ignores model folder when building the bot
Samuele Lorefice
2024-12-26 03:22:14 +01:00
b74e5d75e1
Fixed code, enabled to also always answer in a private chat
Samuele Lorefice
2024-12-26 01:34:10 +01:00
2357c7570c
Added llama.cpp and reworked the code
Samuele Lorefice
2024-12-26 00:35:00 +01:00
c6302112b2
Implemented also OpenAI
Samuele Lorefice
2024-12-25 21:38:26 +01:00
4b308b762a
Added LMStudio client, upgraded to .net 9.0
Samuele Lorefice
2024-12-25 19:37:14 +01:00
0ba298b955
Base commit
Samuele Lorefice
2024-12-24 23:08:08 +01:00