CoolFace
Modelpublic

RichardErkhov/jiogenes_-_gpt2-medium-finetuned-open-korean-instructions-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes321downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gpt2-medium-finetuned-open-korean-instructions - GGUF

  • —Model creator: https://huggingface.co/jiogenes/
  • —Original model: https://huggingface.co/jiogenes/gpt2-medium-finetuned-open-korean-instructions/
NameQuant methodSize
gpt2-medium-finetuned-open-korean-instructions.Q2_K.ggufQ2_K0.17GB
gpt2-medium-finetuned-open-korean-instructions.Q3_K_S.ggufQ3KS0.19GB
gpt2-medium-finetuned-open-korean-instructions.Q3_K.ggufQ3_K0.21GB
gpt2-medium-finetuned-open-korean-instructions.Q3_K_M.ggufQ3KM0.21GB
gpt2-medium-finetuned-open-korean-instructions.Q3_K_L.ggufQ3KL0.23GB
gpt2-medium-finetuned-open-korean-instructions.IQ4_XS.ggufIQ4_XS0.22GB
gpt2-medium-finetuned-open-korean-instructions.Q4_0.ggufQ4_00.23GB
gpt2-medium-finetuned-open-korean-instructions.IQ4_NL.ggufIQ4_NL0.23GB
gpt2-medium-finetuned-open-korean-instructions.Q4_K_S.ggufQ4KS0.23GB
gpt2-medium-finetuned-open-korean-instructions.Q4_K.ggufQ4_K0.25GB
gpt2-medium-finetuned-open-korean-instructions.Q4_K_M.ggufQ4KM0.25GB
gpt2-medium-finetuned-open-korean-instructions.Q4_1.ggufQ4_10.25GB
gpt2-medium-finetuned-open-korean-instructions.Q5_0.ggufQ5_00.27GB
gpt2-medium-finetuned-open-korean-instructions.Q5_K_S.ggufQ5KS0.27GB
gpt2-medium-finetuned-open-korean-instructions.Q5_K.ggufQ5_K0.29GB
gpt2-medium-finetuned-open-korean-instructions.Q5_K_M.ggufQ5KM0.29GB
gpt2-medium-finetuned-open-korean-instructions.Q5_1.ggufQ5_10.29GB
gpt2-medium-finetuned-open-korean-instructions.Q6_K.ggufQ6_K0.32GB
gpt2-medium-finetuned-open-korean-instructions.Q8_0.ggufQ8_00.41GB

Original model description: Entry not found