RayIsLazy

joined 1 year ago
sorted by: new top controversial old
Qwen-72B released in c/localllama@poweruser.forum
[–] RayIsLazy@alien.top 1 points 11 months ago

Today is the 1 year anniversary of chatgpt.

Deepseek llm 67b Chat & Base in c/localllama@poweruser.forum
[–] RayIsLazy@alien.top 1 points 11 months ago

their code models are extremely good so I have high hopes for these.

New APU’s close to Gpu processing, but with unlimited memory? in c/localllama@poweruser.forum
[–] RayIsLazy@alien.top 1 points 11 months ago (1 children)

The new oryon cpu from Qualcomm looks pretty good, pretty much better than m2 but for windows.

I have given llama.cpp server ui a facelift in c/localllama@poweruser.forum
[–] RayIsLazy@alien.top 1 points 11 months ago (1 children)

how do i run it? When I build it and run ./server it just shows the default ui

7B models keep repeating/glitching after certain number of tokens in c/localllama@poweruser.forum
[–] RayIsLazy@alien.top 1 points 11 months ago

I had this using other clients, try lm studio with a gguf and chatml, works well for me.

Intel's neural-chat-7b-v3-1 dropped in c/localllama@poweruser.forum
[–] RayIsLazy@alien.top 1 points 11 months ago (3 children)

Wish they'd use chatml...

ORCA 2 Released open source! in c/localllama@poweruser.forum
[–] RayIsLazy@alien.top 1 points 11 months ago

Will they release the dataset so we can try it out on mistral?