LocalLLaMA

2823 readers

16 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]

Llama 3.3 70b - End of open-weight pretrained models from Meta or just a better Llama 3.1 405b finetune? (lemmy.dbzer0.com)

submitted 4 months ago by [email protected] to c/[email protected]

6 comments fedilink hide all child comments

People are talking about the new Llama 3.3 70b release, which has generally better performance than Llama 3.1 (approaching 3.1's 405b performance): https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_3

However, something to note:

Llama 3.3 70B is provided only as an instruction-tuned model; a pretrained version is not available.

Is this the end of open-weight pretrained models from Meta, or is Llama 3.3 70b instruct just a better-instruction-tuned version of a 3.1 pretrained model?

Comparing the model cards: 3.1: https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md 3.3: https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md

The same knowledge cutoff, same amount of training data, and same training time give me hope that it's just a better finetune of maybe Llama 3.1 405b.

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 4 points 4 months ago (1 children)

On Huggingface, someone said it's still the same base model: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/discussions/10

And I remember watching some interview with Zuckerberg this year, where he said releasing the models to the public, including base models, is what he wants and part of their strategy.

[–] [email protected] 2 points 3 months ago

Thank you so much, that exactly answers my question with the official response (that guy works at Meta) that confirms it's the same base model!

I was concerned primarily because in the release notes it strangely didn't mention it anywhere, and I thought it would have been important enough to mention.