README.md

metadata

license: cc-by-nc-4.0

weblab-10b-instruction-sft

Overview

This repository provides a Japanese-centric multilingual GPT-NeoX model of 10 billion parameters.

• Library

  The model was trained using code based on EleutherAI/gpt-neox.

• Model architecture

  A 36-layer, 4864-hidden-size transformer-based language model.

• Pre-training

  The model was trained on around 600B tokens from a mixture of the following corpora

  • Japanese C4
  • The Pile

• Instruction-supervised-finetuning

  The model was finetuned on a subset records from a mixture of the following dataset

  • Alpaca (English)
  • Alpaca (Japanese translation)
  • Flan 2021 (English)
  • Flan CoT (English)
  • Flan Dialog (English)

• Model Series

  Variant	Link
  weblab-10b-instruction-sft	https://huggingface.co/matsuo-lab/weblab-10b-instruction-sft
  weblab-10b	https://huggingface.co/matsuo-lab/weblab-10b

• Authors

  Takeshi Kojima

---

Benchmarking

• Japanese benchmark

  • We used Stability-AI/lm-evaluation-harness library for evaluation.
  • The 4-task average accuracy is based on results of JCommonsenseQA-1.1, JNLI-1.1, MARC-ja-1.1, and JSQuAD-1.1.
  • model loading is performed with float16, and evaluation is performed with template version 0.3 using the few-shot in-context learning.
  • The number of few-shots is 3,3,3,2.

  Model	Average	JCommonsenseQA	JNLI	MARC-ja	JSQuAD
  weblab-10b-instruction-sft	78.78	74.35	65.65	96.06	79.04
  weblab-10b	66.38	65.86	54.19	84.49	60.98

---

How to use the model

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("matsuo-lab/weblab-10b-instruction-sft")
model = AutoModelForCausalLM.from_pretrained("matsuo-lab/weblab-10b-instruction-sft")

if torch.cuda.is_available():
    model = model.to("cuda")

text = "大規模言語モデルについて説明してください。"
text = f'以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。\n\n### 指示:\n{text}\n\n### 応答:'
token_ids = tokenizer.encode(text, add_special_tokens=False, return_tensors="pt")

with torch.no_grad():
    output_ids = model.generate(
        token_ids.to(model.device),
        max_new_tokens=100,
        do_sample=True,
        temperature=0.5,
        top_p=0.9,
        pad_token_id=tokenizer.pad_token_id,
        bos_token_id=tokenizer.bos_token_id
    )

output = tokenizer.decode(output_ids.tolist()[0])
print(output)

---

Licenese

cc-by-nc-4.0