weblab-10b / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
e21e592
|
raw
history blame
4.29 kB
metadata
license: cc-by-nc-4.0

weblab-10b

Overview

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


Benchmarking

  • Japanese benchmark : JGLUE 8-task (2023-08-27)

    • We used Stability-AI/lm-evaluation-harness library for evaluation.
    • The 8-task average accuracy is based on results of JCommonsenseQA-1.1, JNLI-1.1, MARC-ja-1.1, JSQuAD-1.1, jaqket_v2-0.2, xlsum_ja-1.0, xwinograd_ja, and mgsm-1.0.
    • 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 3,3,3,2,1,1,0,5.
    • special_tokens_map.json is modified to avoid errors during the evaluation of the second half benchmarks. As a result, the results of the first half benchmarks became slightly different.
    model average jcommonsenseqa jnli marc_ja jsquad jaqket_v2 xlsum_ja xwinograd_ja mgsm
    weblab-10b-instruction-sft 59.11 74.62 66.56 95.49 78.34 63.32 20.57 71.95 2
    weblab-10b 50.74 66.58 53.74 82.07 62.94 56.19 10.03 71.95 2.4
  • Japanese benchmark : JGLUE 4-task (2023-08-18)

    • 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")
model = AutoModelForCausalLM.from_pretrained("matsuo-lab/weblab-10b", torch_dtype=torch.float16)

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

text = "吾輩は猫である。"
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=0.7,
        top_p=0.95
    )

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

Licenese

cc-by-nc-4.0

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 33.76
ARC (25-shot) 39.51
HellaSwag (10-shot) 65.76
MMLU (5-shot) 26.29
TruthfulQA (0-shot) 36.02
Winogrande (5-shot) 62.51
GSM8K (5-shot) 1.44
DROP (3-shot) 4.81