This is a more recent merge of Chansung's Alpaca Lora which was updated using the clean alpaca dataset as of 04/06/2023 with refined training parameters

Training Parameters

num_epochs=10
cutoff_len=512
group_by_length
lora_target_modules='[q_proj,k_proj,v_proj,o_proj]'
lora_r=16
micro_batch_size=8

Benchmarks

Wikitext2: 4.473957061767578

Ptb-New: 8.682597160339355

C4-New: 6.517213344573975

Note: This version uses --groupsize 128, resulting in better evaluations. However, it consumes more VRAM.

MetaIX/Alpaca-30B-Int4-128G-Safetensors

MetaIX/
Alpaca-30B-Int4-128G-Safetensors