Join the Coffee & AI Discord for AI Stuff and things!
[![Discord](https://img.shields.io/discord/232596713892872193?logo=discord)](https://discord.gg/2JhHVh7CGu)


https://huggingface.co/TheBloke/Llama-2-13B-GGML
https://huggingface.co/TheBloke/Llama-2-13B-GPTQ


## Training procedure

PEFT:

The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32

This ran on for 3500 -- 3 epochs on an in testing storywriting dataset. Training took 14 hours on a 3090 Ti.