Japanese
gpt_neox
japanese
causal-lm
stormy-7b-10ep / README.md
retarfi's picture
Update README.md
41cf1e0
|
raw
history blame
1.38 kB
metadata
license: cc-by-sa-4.0
datasets:
  - izumi-lab/llm-japanese-dataset-vanilla
language:
  - ja
tags:
  - gpt_neox
  - japanese
  - causal-lm

This repo contains a low-rank adapter for CALM fit on the dataset specially extracted from llm-japanese-dataset.

You can test this at https://huggingface.co/spaces/izumi-lab/stormy-7b-10ep

This version of the weights was trained with the following hyperparameters:

  • Epochs: 10
  • Batch size: 128
  • Cutoff length: 300
  • Learning rate: 3e-4
  • Lora r: 4
  • Lora target modules: query_key_value
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = "cyberagent/open-calm-7b"
model = AutoModelForCausalLM.from_pretrained(base_model, torch_dtype=torch.float16)
tokenizer = AutoTokenizer.from_pretrained(base_model)
model = PeftModel.from_pretrained(
    model,
    "izumi-lab/stormy-7b-10ep",
    torch_dtype=torch.float16,
)

To see more latest information, please go to llm.msuzuki.me.

Details

Citation: TBD

If you have any inquiries, such as joint research, data provision, various types of support, please email izumi-llm@socsim.org .