this post was submitted on 10 Nov 2023
1 points (100.0% liked)

LocalLLaMA

3 readers
1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago
MODERATORS
communick@poweruser.forum
1
Finetuning LLMs: Does it add new knowledge to model or not? (alien.top)
submitted 1 year ago by Euphoric-Nebula-4559@alien.top to c/localllama@poweruser.forum
8 comments fedilink hide all child comments
 

Can you share your experiences?

you are viewing a single comment's thread
view the rest of the comments
[โ€“] kristaller486@alien.top 1 points 1 year ago (1 children)

Full-weight fine-tuning should add new knowledge. Not LoRa.

[โ€“] Euphoric-Nebula-4559@alien.top 1 points 1 year ago

Any repo for llama-2 to do this?