gpt4all

You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

History

cebtenzzre 8d7a3f26d3 gpt4all-training: delete old chat executables Signed-off-by: cebtenzzre <cebtenzzre@gmail.com>		7 months ago
..
configs	fix: update train scripts and configs for other models (#1164 )	10 months ago
figs	mono repo structure	1 year ago
GPT-J_MAP.md	mono repo structure	1 year ago
README.md	fix(training instructions): model repo name (#728 )	12 months ago
TRAINING_LOG.md	mono repo structure	1 year ago
build_map.py	make scripts executable (#1555 )	7 months ago
clean.py	make scripts executable (#1555 )	7 months ago
create_hostname.sh	make scripts executable (#1555 )	7 months ago
data.py	fix: update train scripts and configs for other models (#1164 )	10 months ago
env.yaml	mono repo structure	1 year ago
eval_figures.py	make scripts executable (#1555 )	7 months ago
eval_self_instruct.py	make scripts executable (#1555 )	7 months ago
generate.py	make scripts executable (#1555 )	7 months ago
inference.py	make scripts executable (#1555 )	7 months ago
launcher.sh	make scripts executable (#1555 )	7 months ago
old-README.md	contributing and readme	1 year ago
read.py	mono repo structure	1 year ago
requirements.txt	fix: update train scripts and configs for other models (#1164 )	10 months ago
train.py	make scripts executable (#1555 )	7 months ago

README.md

Training GPT4All-J

Please see GPT4All-J Technical Report for details.

GPT4All-J Training Data

We are releasing the curated training data for anyone to replicate GPT4All-J here: GPT4All-J Training Data
- Atlas Map of Prompts
- Atlas Map of Responses

We have released updated versions of our GPT4All-J model and training data.

v1.0: The original model trained on the v1.0 dataset
v1.1-breezy: Trained on a filtered dataset where we removed all instances of AI language model
v1.2-jazzy: Trained on a filtered dataset where we also removed instances like I'm sorry, I can't answer... and AI language model

The models and data versions can be specified by passing a revision argument.

For example, to load the v1.2-jazzy model and dataset, run:

from datasets import load_dataset
from transformers import AutoModelForCausalLM

dataset = load_dataset("nomic-ai/gpt4all-j-prompt-generations", revision="v1.2-jazzy")
model = AutoModelForCausalLM.from_pretrained("nomic-ai/gpt4all-j", revision="v1.2-jazzy")

GPT4All-J Training Instructions

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_gptj.json train.py --config configs/train/finetune_gptj.yaml