Fix security issue or ignore false positives

Apply isort then black

Lint finetune.py

Lint and format

bnb fixes

refactor: fix previous refactors

Refactor to use DictDefault instead

Fix load error

Convert attrdict to addict

move list not in list logic to fn

load the tokenizer seperately from the model

add logging and make sure model unloads to float16

remove un-needed code, add validation

Update scripts/finetune.py

Update scripts/finetune.py for logging

optionally be able to specify alpaca or chat style prompts

add alpaca multiple choice instruct dataset support

reorder options so debug can happen in the same prepare step

more fixes

Fix typo

black formatting

Update finetune.py

Don't save full model for lora

Save adapter for lora

fix whitespace and instruction on inference

refactor inference, warn if model is frozen

support for multi line inference input, log sweep over learning rates

support llama-adapter zero init attention

fix sharegpt tokenization, refactor tokenization debugging

various bugfixes

improve inference

quickstart instructions for starting from runpod (#5)

WIP large refactor to make finetune script a little more manageable (#3)

add support for alpaca reflect training (#2)

Tokenization open assistant (#1)

fix llama check

fix conditional check to prevent always using 4bit

imrpove llama check and fix safetensors file check

suppport for alpaca-like instruction datasets without inputs

casts the prepared data to int16 (doesn't help with training memory)

bugfixes

fix lora target module, require explicit flash attention, fix min logging steps, don't use adam8bit for int4, hash prepared datasets, support hf hub datasets

4bit quantized support (wip)

cleanup, prep for 4bit quant support

deepspeed doesn't work with flash-attn, and the gpu savings w flash attn are better than the deepspeed headaches

fix logging

prepare datasets only flag

configure log level, add llama 7b config

more logging, wandb fixes

refactor trainer setup to account for deepspeed integration