Monero/oasst-llama-13b-4-epochs-4bit-128g

Information

OpenAssistant-Llama-13B-4-bit working with GPTQ versions used in Oobabooga's Text Generation Webui and KoboldAI.
This was made using Serpdotai's Open Assistant 13b LoRa trained for 4 epochs using Open Assistant's dataset.

python llama.py /KoboldAI/repos/gptq/llama13b-oasst-4-epochs-lora c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors llama13b-oasst-4-epochs-lora-4bit-128g.safetensors

Benchmarks

--true-sequential --groupsize 128

Wikitext2: 5.380471229553223

Ptb-New: 31.921072006225586

C4-New: 7.140256881713867

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