gpt4all: an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue
Go to file
2023-03-27 16:33:00 +00:00
configs feat: update embeddings 2023-03-26 17:45:21 +00:00
peft@098962fa65 feat: peft submodule 2023-03-25 16:23:14 +00:00
transformers@cae78c46d6 feat: transformers submodule, gitignore 2023-03-25 16:16:11 +00:00
.gitignore chore: gitignore 2023-03-27 16:33:00 +00:00
.gitmodules feat: peft submodule 2023-03-25 16:23:14 +00:00
clean.py fix: clean, print num rows 2023-03-27 16:27:11 +00:00
data.py fix: eos conditional, watermark 2023-03-27 16:29:43 +00:00
env.yaml feat: env for conda, pip 2023-03-25 16:16:40 +00:00
generate.py fix: don't print token ids of output 2023-03-25 17:18:07 +00:00
read.py feat: train and clean data 2023-03-25 16:17:48 +00:00
README.md fix: update to how to train 2023-03-25 21:57:01 +00:00
requirements.txt feat: env for conda, pip 2023-03-25 16:16:40 +00:00
train.py fix: add epoch train 2023-03-27 16:32:35 +00:00

gpt4all

Setup

Clone the repo

git clone --recurse-submodules git@github.com:nomic-ai/gpt4all.git

Setup the environment

python -m pip install -r requirements.txt

cd transformers
pip install -e . 

cd ../peft
pip install -e .

Generate

python generate.py --config configs/generate/generate.yaml --prompt "Write a script to reverse a string in Python

Train

accelerate launch --dynamo_backend=inductor --num_processes=8 --num_machines=1 --machine_rank=0 --deepspeed_multinode_launcher standard --mixed_precision=bf16 --use_deepspeed --deepspeed_config_file=configs/deepspeed/ds_config.json train.py --config configs/train/finetune-7b.yaml