Fine-Tuning LLMs to 1.58bit
huggingface.co
Fine-Tuning LLMs to 1.58bit
1–4 of 4 posts
Re: Fine-Tuning LLMs to 1.58bit
#2Very 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!
Re: Fine-Tuning LLMs to 1.58bit
#3That'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.
Re: Fine-Tuning LLMs to 1.58bit
#4That'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.
the performance is still a bit degraded though.