README.md

Information

GPT4-X-Alpaca 30B 4-bit working with GPTQ versions used in Oobabooga's Text Generation Webui and KoboldAI.

There are 3 quantized versions, one is quantized using GPTQ's --true-sequential and --act-order optimizations, the second is quantized using GPTQ's --true-sequential and --groupsize 128 optimization, and the third one is quantized for GGML using q4_1

This was made using Chansung's GPT4-Alpaca Lora: https://huggingface.co/chansung/gpt4-alpaca-lora-30b

GPU/GPTQ Usage

To use with your GPU using GPTQ pick one of the .safetensors along with all of the .jsons and .model files.

Oobabooga: If you require further instruction, see https://github.com/oobabooga/text-generation-webui/blob/main/docs/GPTQ-models-(4-bit-mode).md and https://github.com/oobabooga/text-generation-webui/blob/main/docs/LLaMA-model.md

KoboldAI: If you require further instruction, see https://github.com/0cc4m/KoboldAI

CPU/GGML Usage

To use your CPU using GGML(Llamacpp) you only need the single .bin ggml file.

Oobabooga: If you require further instruction, see https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md

KoboldAI: If you require further instruction, see https://github.com/LostRuins/koboldcpp

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

--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.