vihangd / alpaca-qlora

Instruct-tune Open LLaMA / RedPajama / StableLM models on consumer hardware using QLoRA

vihangd/alpaca-qlora Issues

Lora
Updated 3 months ago1
Using alpaca format for the Databricks Dolly 15k dataset
Closed 10 months ago2
newbie question about 4bit quantization
Updated 10 months ago
8-bit Adam vs 32-bit Adam ??
Updated 10 months ago
Question on differences with artidoro/qlora
Updated a year ago1
ValueError: test_size=2000 should be either positive and smaller than the number of samples 2 or a float in the (0, 1) range
Updated a year ago1
Can you please share the results you get with the trained models?
Closed a year ago10