RoPE Scaled QLoRA Finetune of airoboros-33b-gpt4-1.4.1 (LoRA)

Full model card with merged GPTQ 4bit quantized weights can be found here: https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-GPTQ

fp16 merged weights can be found here: https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-fp16

Overview

This is Jon Durbin's Airoboros 33B GPT4 1.4 (LoRA weights) with several key modifications:

• Context length extended to 8192 by RoPE Scaled Embeddings, but NOT via the superHOT LoRA. I started with base Llama-33b.
• Training sequences beyond 2048 have the target truncated to equal 2048.
• Used airoboros-gpt4-1.4.1 dataset instead of airoboros-gpt4-1.4

Otherwise, I emulated the training process as closely as possible (rank 64 QLoRA) It was trained on 1x RTX 6000 Ada for ~43 hours.