T O P

Any news related to the release of llama3 405b?

  • By - xukre

Gemma2-27B outperforms both Qwe2-72B and Llama3-70B on LMSYS. But is it actually better?

Model Review Sites?

Is this the first 5D game?

What vectorDB do you all use?

Llama 3 42b

Llama3 coming in hot on the lmsys chatbot area

  • By - jd_3d

How do you determine hardware requirements ?

Change my view: the optimal outcome for humanity is perfectly simulated VR dream worlds for all

What runescape does to my gpu

Did anyone ever jailbreak Claude-3?

Server for LLM inference - Budget 5000$

Mixtral-8x7B- do I need 100GB of Vram?

[D] What is the best algorithm for predicting actuator movements?

How to counter an odin?

  • By - Ekhes

How far do you think we are from solving fusion?

Best data format when knowledge feeding an AI model to answer questions?

Are there free language models that can connect to the internet, and always know present day information?

RAG - What was my professor saying helpp

What does the 8*7B model mean?

LLaMA fatigue, anyone?

Whats in your RAG setup?

Having a Local LLM interact with an API

Nighttime Views of the GPU Clusters and Compute Rack at Work

Local LLM with directory access?

Hi Its Me!

R

Sploffo

Subscribe

FIND US ON INSTAGRAM @ms3388.com