HF中国镜像站's logo

iljoo
/
iljoo-chatbot-8b-test

Safetensors
Model card Files Community

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.

Base model

MLP-KTLim/llama-3-Korean-Bllossom-8B

Dataset

  1. AIHub : 한국어 성능이 개선된 초거대 AI 언어모델 개발 및 데이터
    • 데이터 소개 : 한국어 말뭉치 데이터 20억 어절/310만 건과 RLHF 데이터 7만 7천건으로 구성 됨
    • RLHF 데이터 > SFT 데이터 10,579개 데이터 활용
  2. 재정정보 AI 검색 알고리즘 경진대회 데이터
    • 데이터 소개 : 중앙정부 재정 정보 관련 질의 응답 데이터
    • train dataset : 498개 데이터 활용

Data structure

  • Data format
    • {instruction:, response:}

Parameter

[2024.10.24]

  • QLoRA : Rank 4
  • max_length : 512
  • Epoch : 10
Downloads last month

-

Downloads are not tracked for this model. How to track
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 iljoo/iljoo-chatbot-8b-test

Base model

meta-llama/Meta-Llama-3-8B
Finetuned
MLP-KTLim/llama-3-Korean-Bllossom-8B
Finetuned
(35)
this model

Dataset used to train iljoo/iljoo-chatbot-8b-test