CoolFace
Modelpublic

RichardErkhov/lcw99_-_llama-3-10b-ko-240604-e2f-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes1.2kdownloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3-10b-ko-240604-e2f - GGUF

  • —Model creator: https://huggingface.co/lcw99/
  • —Original model: https://huggingface.co/lcw99/llama-3-10b-ko-240604-e2f/
NameQuant methodSize
llama-3-10b-ko-240604-e2f.Q2_K.ggufQ2_K3.56GB
llama-3-10b-ko-240604-e2f.IQ3_XS.ggufIQ3_XS3.94GB
llama-3-10b-ko-240604-e2f.IQ3_S.ggufIQ3_S4.13GB
llama-3-10b-ko-240604-e2f.Q3_K_S.ggufQ3KS4.11GB
llama-3-10b-ko-240604-e2f.IQ3_M.ggufIQ3_M4.25GB
llama-3-10b-ko-240604-e2f.Q3_K.ggufQ3_K4.52GB
llama-3-10b-ko-240604-e2f.Q3_K_M.ggufQ3KM4.52GB
llama-3-10b-ko-240604-e2f.Q3_K_L.ggufQ3KL4.88GB
llama-3-10b-ko-240604-e2f.IQ4_XS.ggufIQ4_XS5.05GB
llama-3-10b-ko-240604-e2f.Q4_0.ggufQ4_05.26GB
llama-3-10b-ko-240604-e2f.IQ4_NL.ggufIQ4_NL5.31GB
llama-3-10b-ko-240604-e2f.Q4_K_S.ggufQ4KS5.29GB
llama-3-10b-ko-240604-e2f.Q4_K.ggufQ4_K5.56GB
llama-3-10b-ko-240604-e2f.Q4_K_M.ggufQ4KM5.56GB
llama-3-10b-ko-240604-e2f.Q4_1.ggufQ4_15.79GB
llama-3-10b-ko-240604-e2f.Q5_0.ggufQ5_06.33GB
llama-3-10b-ko-240604-e2f.Q5_K_S.ggufQ5KS6.33GB
llama-3-10b-ko-240604-e2f.Q5_K.ggufQ5_K6.49GB
llama-3-10b-ko-240604-e2f.Q5_K_M.ggufQ5KM6.49GB
llama-3-10b-ko-240604-e2f.Q5_1.ggufQ5_16.87GB
llama-3-10b-ko-240604-e2f.Q6_K.ggufQ6_K7.48GB
llama-3-10b-ko-240604-e2f.Q8_0.ggufQ8_09.68GB

Original model description: --- language:

  • —ko license: apache-2.0 library_name: transformers ---

Model Card for Model ID

Model Details

Model Description

Korean layer added instruction tunning of meta-llama/Meta-Llama-3-8B-Instruct

Chat template

tokenizer.applychattemplate(chat, tokenize=False)