Information
GPT4-X-Alpaca 30B 4-bit working with GPTQ versions used in Oobabooga's Text Generation Webui and KoboldAI.There are 2 quantized versions, one is using --true-sequential and --act-order optimizations, and the other is using --true-sequential and --groupsize 128 optimizations.
This was made using Chansung's GPT4-Alpaca Lora: https://huggingface.co/chansung/gpt4-alpaca-lora-30bTraining 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
--true-sequential --act-order
Wikitext2: 4.481280326843262
Ptb-New: 8.539161682128906
C4-New: 6.451964855194092
Note: This version does not use --groupsize 128, therefore evaluations are minimally higher. However, this version allows fitting the whole model at full context using only 24GB VRAM.
--true-sequential --groupsize 128
Wikitext2: 4.285132884979248
Ptb-New: 8.34856128692627
C4-New: 6.292652130126953
Note: This version uses --groupsize 128, resulting in better evaluations. However, it consumes more VRAM.