21·
2 months agoaya based llms are extremely powerful. same with qwen
Software Engineer living in İstanbul.
- 0 Posts
- 4 Comments
Joined 2 months ago
Cake day: September 18th, 2024
You are not logged in. If you use a Fediverse account that is able to follow users, you can follow this user.
T5 is a very mediocre LM. why do people keep using it?
quite the opposite. Lora’s are very effective against catastrophic forgetting, and full finetuning is very dangerous (but also much more powerful).
qwen2.5 just came out, and looks amazing. You can try it with ollama.