[HN Gopher] Fine-Tuning LLMs to 1.58bit
___________________________________________________________________
Fine-Tuning LLMs to 1.58bit
Author : galeos
Score : 44 points
Date : 2024-09-18 15:33 UTC (7 hours ago)
(HTM) web link (huggingface.co)
(TXT) w3m dump (huggingface.co)
| amilios wrote:
| Very exciting, although it was a bit disappointing to see that
| they're hitting just llama1 7b performance by quantizing llama3.
| but i'm sure the performance gap will close over time!
| patleeman wrote:
| That's awesome. The original discussion of bitnet made it seem
| like you needed to train a model from scratch but its neat they
| were able to adapt an existing model. This is quite exciting.
___________________________________________________________________
(page generated 2024-09-18 23:02 UTC)