submitted 10 months ago by [email protected] to c/[email protected]

11 comments fedilink hide all child comments

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.

top 11 comments

sorted by: hot top new old

[-] [email protected] 6 points 10 months ago

llama.cpp and ollama already support it!

https://ollama.com/library/llama3.1

[-] [email protected] 1 points 10 months ago

It doesn't follow instructions, insists on being "conversational" despite being told not to be.

[-] [email protected] 3 points 10 months ago

that is the base model. Wait for people to finetune it for spesfic tasks

[-] [email protected] -1 points 10 months ago

Probably not foss

[-] [email protected] 8 points 10 months ago

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

[-] [email protected] 5 points 10 months ago

The license has limitations and isn't something standard like Apache

[-] [email protected] 5 points 10 months ago

True, but it hardly matters for the source since the architecture is pulled into open source projects like transformers (Apache) and llama.cpp (MIT). The weights remain under the dubious Llama Community License, so I would only call the data “available” instead of “open”.

[-] [email protected] 4 points 10 months ago

I'll just stick to Mistral

[-] [email protected] 1 points 10 months ago

Are you using mistral 7B?

I also really like that model and their fine-tunes. If licensing is a concern, it's definitely a great choice.

Mistral also has a new model, Mistral Nemo. I haven't tried it myself, but I heard it's quite good. It's also licensed under Apache 2.0 as far as I know.

[-] [email protected] 3 points 10 months ago* (last edited 10 months ago)

Is it part of ollama?

Edit: https://ollama.com/library/mistral-nemo

[-] [email protected] 2 points 10 months ago

Yes, you can find it here.

this post was submitted on 23 Jul 2024

44 points (90.7% liked)

LocalLLaMA

3040 readers

50 users here now

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

founded 2 years ago

MODERATORS

[email protected]