CoolFace
Modelpublic

RichardErkhov/ragbox_-_Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes846downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3-Open-Ko-8B-Instruct-hr241226ver1 - GGUF

  • —Model creator: https://huggingface.co/ragbox/
  • —Original model: https://huggingface.co/ragbox/Llama-3-Open-Ko-8B-Instruct-hr241226ver1/
NameQuant methodSize
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q2_K.ggufQ2_K2.96GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.IQ3_XS.ggufIQ3_XS0.41GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.IQ3_S.ggufIQ3_S0.41GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q3_K_S.ggufQ3KS3.41GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.IQ3_M.ggufIQ3_M3.52GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q3_K.ggufQ3_K3.74GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q3_K_M.ggufQ3KM3.74GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q3_K_L.ggufQ3KL4.03GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.IQ4_XS.ggufIQ4_XS4.18GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q4_0.ggufQ4_04.34GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.IQ4_NL.ggufIQ4_NL4.38GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q4_K_S.ggufQ4KS4.37GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q4_K.ggufQ4_K4.58GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q4_K_M.ggufQ4KM4.58GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q4_1.ggufQ4_14.78GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q5_0.ggufQ5_05.21GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q5_K_S.ggufQ5KS5.21GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q5_K.ggufQ5_K5.34GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q5_K_M.ggufQ5KM5.34GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q5_1.ggufQ5_15.65GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q6_K.ggufQ6_K6.14GB
Llama-3-Open-Ko-8B-Instruct-hr_241226_ver1.Q8_0.ggufQ8_07.95GB

Original model description: --- base_model: beomi/Llama-3-Open-Ko-8B-Instruct-preview tags:

  • —text-generation-inference
  • —transformers
  • —unsloth
  • —llama
  • —trl license: apache-2.0 language:
  • —en ---

Uploaded model

  • —Developed by: ragbox
  • —License: apache-2.0
  • —Finetuned from model : beomi/Llama-3-Open-Ko-8B-Instruct-preview

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>