zlacker
[return to "Fine-tune your own Llama 2 to replace GPT-3.5/4"]
◧
1. divbze+HE
[view]
[source]
2023-09-12 19:30:20
>>kcorbi+(OP)
Is Llama 2 currently the way to go for fine-tuning your own models? Are there other open-source LLMs worth considering?
◧◩
2. daemon+go1
[view]
[source]
2023-09-12 22:32:22
>>divbze+HE
We've found Flan-T5 to be useful for text-to-text (mostly document QA). Haven't done a lot of testing on fine-tuning yet though.
[go to top]