Danny_Davitoe

joined 1 year ago
[–] Danny_Davitoe@alien.top 1 points 11 months ago

U-Amethyst-20B is very good, it takes a few tries to get something unworldly good. Like a 1 in 3 chance to get something amazing. I am still trying out prompts to make it more consistent.

[–] Danny_Davitoe@alien.top 1 points 1 year ago

Yeah, don't want to spill your drink

[–] Danny_Davitoe@alien.top 1 points 1 year ago

Is there an example of a prompt and the model's response?

 

Was wondering if anyone had guide or some code to get started on Lora training. I want to get started on creating a customized Llama2 model with a small dataset that I created. Was wondering if anyone had a good starting point.