You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Gemma 2 Quantized for ELYZA-tasks-100-TV

このモデルは、LLM講義2024最終課題のために作成された量子化版Gemma 2モデルです。

モデルの説明

  • ベースモデル: google/gemma-2b-it
  • 適用した変更: 4bit量子化による最適化
  • 用途: ELYZA-tasks-100-TVベンチマーク対応
  • メモリ使用量: 約8GB VRAM
  • 推論時間: 全タスク1時間以内

環境要件

  • Python 3.8+
  • NVIDIA GPU (VRAM 24GB以上推奨)
  • CUDA 11.8+

必要なパッケージ

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
pip install transformers
pip install accelerate
pip install bitsandbytes
Downloads last month
0
Safetensors
Model size
1.55B params
Tensor type
F32
·
FP16
·
U8
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for Guchyos/gemma-2b-elyza-task

Base model

google/gemma-2b-it
Quantized
(31)
this model

Dataset used to train Guchyos/gemma-2b-elyza-task

Space using Guchyos/gemma-2b-elyza-task 1