LocalLLaMA @sh.itjust.works Bazsalanszky @lemmy.toldi.eu 4 mo. ago

Llama 3.1 is out!

ai.meta.com Introducing Llama 3.1: Our most capable models to date

Bringing open intelligence to all, our latest models expand context length, add support across eight languages, and include Meta Llama 3.1 405B— the first frontier-level open source AI model.

Meta has released llama 3.1. It seems to be a significant improvement to an already quite good model. It is now multilingual, has a 128k context window, has some sort of tool chaining support and, overall, performs better on benchmarks than its predecessor.

With this new version, they also released their 405B parameter version, along with the updated 70B and 8B versions.

I've been using the 3.0 version and was already satisfied, so I'm excited to try this.

ChatGPT @lemmy.world lawrence @lemmy.world 4 mo. ago

Llama 3.1 (already available in ollama) was release with many improvements since Llama 3

ai.meta.com /blog/meta-llama-3-1/

11 comments

llama.cpp and ollama already support it!

https://ollama.com/library/llama3.1
It doesn't follow instructions, insists on being "conversational" despite being told not to be.
- that is the base model. Wait for people to finetune it for spesfic tasks
Probably not foss
- the code is FOSS, the weights aren't, this is pretty common with e.g. FOSS games, the only difference here is weights are much costlier to remake from scratch than game assets
  
  The license has limitations and isn't something standard like Apache

You've viewed 11 comments.