werty1248/Llama-3-Ko-8B-Instruct-AOG

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kLicense:llama3Architecture:Transformer Warm

werty1248/Llama-3-Ko-8B-Instruct-AOG is an 8 billion parameter instruction-tuned Llama 3 model, fine-tuned from beomi/Llama-3-Open-Ko-8B. This model specializes in Korean language instruction following, leveraging datasets like KoAlpaca-v1.1a, OpenOrca-KO, and openassistant-guanaco-ko. It is optimized for detailed and friendly conversational responses in Korean, showing improved accuracy on the kobest_boolq benchmark.

Loading preview...

Overview

werty1248/Llama-3-Ko-8B-Instruct-AOG is an 8 billion parameter instruction-tuned model based on the Llama 3 architecture, specifically fine-tuned from beomi/Llama-3-Open-Ko-8B. This model is designed for enhanced instruction following in the Korean language.

Key Capabilities

  • Korean Instruction Following: Optimized for generating detailed and friendly responses to user instructions in Korean.
  • Dataset Integration: Trained on a combination of commercially available Korean datasets, including beomi/KoAlpaca-v1.1a, kyujinpy/OpenOrca-KO, and nlpai-lab/openassistant-guanaco-ko.
  • Multi-turn Conversation: Incorporates multi-turn conversation data, though its reliability in this area is noted as lower.
  • Performance: Shows an improvement in accuracy on the kobest_boolq benchmark (0.8312) compared to its base model (0.7963).

Training Details

The model was trained using Axolotl with LoRA for 3 epochs, utilizing a sequence length of 4096 and bf16 precision. Training took approximately 8 hours on a single A100 GPU.

Recommended Usage

It is recommended to use an "Instruction - Input - Response" or "Question - Instruction - Response" format for optimal performance, with the latter often yielding better results. The model aims to provide comprehensive answers without requiring external searches.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p