Spaces:

Dovakiins
/

qwerrwe

Build error

App Files Files Community

qwerrwe / configs

Ctrl+K

Ctrl+K

100 contributors

History: 18 commits

winglian's picture

tweaks to data loading, 8 bit adam, accelerate and deepspeed

097d367 about 2 years ago

accelerate
quickstart instructions for starting from runpod (#5) about 2 years ago
cerebras_1_3B_alpaca.yml
934 Bytes

4bit quantized support (wip) about 2 years ago
gpt_neox_20b.yml
909 Bytes

WIP large refactor to make finetune script a little more manageable (#3) about 2 years ago
llama_13B_alpaca.yml
830 Bytes

tweaks to data loading, 8 bit adam, accelerate and deepspeed about 2 years ago
llama_65B_alpaca.yml
1.05 kB

fix sharegpt handling from hf, don't worry about loading llama if using earlier transformers release about 2 years ago
llama_7B_4bit.yml
975 Bytes

quickstart instructions for starting from runpod (#5) about 2 years ago
llama_7B_alpaca.yml
933 Bytes

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 about 2 years ago
pythia_1_2B_alpaca.yml
978 Bytes

4bit quantized support (wip) about 2 years ago
quickstart.yml
975 Bytes

quickstart instructions for starting from runpod (#5) about 2 years ago
sample.yml
3.66 kB

quickstart instructions for starting from runpod (#5) about 2 years ago
stability_3b.yml
663 Bytes

various bugfixes about 2 years ago
vicuna_13B_4bit_reflect.yml
1.05 kB

add support for alpaca reflect training (#2) about 2 years ago