←back to thread

Show HN: Llama-dl – high-speed download of LLaMA, Facebook's 65B GPT model

(github.com)
343 points sillysaurusx | 3 comments | 05 Mar 23 04:28 UTC | HN request time: 0.822s | source
1. bitL ◴[05 Mar 23 11:05 UTC] No.35028540[source]▶
How does LLaMA handle fast fine-tuning? Are they using transformer adapters for it?
replies(1): >>35031006 #
2. loufe ◴[05 Mar 23 16:23 UTC] No.35031006[source]▶
It's already been adapted for hugging face transformers[1]. Apparently that should unlock its full potential. Oobabooga integrated the change into text-generation-webui[2] meaning we can already access a large chunk of its potential (from what I understand).

[1] https://github.com/huggingface/transformers/pull/21955

[2] https://github.com/oobabooga/text-generation-webui/commit/90...

replies(1): >>35032636 #
3. bitL ◴[05 Mar 23 18:47 UTC] No.35032636[source]▶
That's absolutely fantastic! Thanks for the links!