gpt4all/configs/inference/gptj.yaml
2023-04-07 01:40:39 +00:00

15 lines
257 B
YAML

# model/tokenizer
model_name: "nomic-ai/gpt4all-gptj-multinode-deepspeed-finetuned-epoch_0"
tokenizer_name: "EleutherAI/gpt-j-6B"
# dataset
streaming: false
num_proc: 64
dataset_path: "data_multiplus"
max_length: 1024
batch_size: 32
# logging
seed: 42