clover1980

CPU limit slowing 30B, memory pool limit

7

First of all guys i want to thank you for bringing such great instrument into people's hands. Half of planet countries blocked from ChatGPT already, many still forgetting this. Secondly,...

Shared Youtube link not executed

2

I searched open issues and strangely don't see the fundamental application bug of inability to execute any received Youtube web address link to video. Why it's important? 1)Sharing is a...

Hi, This project is great, but i can't understand how it working with Ollama models but not with current widespread quantization standard as GGUF. Ollama itself don't support GGUF, it...

[UI/UX]: Continue generation button for limited context output

2

### How are you running AnythingLLM? Local development ### What happened? We all know that Deepseek R1 makes a reasoning portion of chat, which in the AnythingLLM abruptly ending unfinished...

Current Readme page are quite messy and very hard to understand for novices. I'm offering to rewriting it into more comsumable form. This description are prepared by Marco O1+Qwen merge...

Something changed in 3.12 degrading models vs 3.9

4

### Describe the bug Does something which was changed in new 3.12 version makes models degrade and hallucinate? I think it is, because i've checked TWICE same model (Kimi K2-Instruct-0905...