RichardErkhov/lcw99_-_llama-3-8b-it-kor-extented-chang-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3-8b-it-kor-extented-chang - GGUF

• Model creator: https://huggingface.co/lcw99/
• Original model: https://huggingface.co/lcw99/llama-3-8b-it-kor-extented-chang/

Name	Quant method	Size
llama-3-8b-it-kor-extented-chang.Q2_K.gguf	Q2_K	2.96GB
llama-3-8b-it-kor-extented-chang.IQ3_XS.gguf	IQ3_XS	3.28GB
llama-3-8b-it-kor-extented-chang.IQ3_S.gguf	IQ3_S	3.43GB
llama-3-8b-it-kor-extented-chang.Q3_K_S.gguf	Q3_K_S	3.41GB
llama-3-8b-it-kor-extented-chang.IQ3_M.gguf	IQ3_M	3.52GB
llama-3-8b-it-kor-extented-chang.Q3_K.gguf	Q3_K	3.74GB
llama-3-8b-it-kor-extented-chang.Q3_K_M.gguf	Q3_K_M	3.74GB
llama-3-8b-it-kor-extented-chang.Q3_K_L.gguf	Q3_K_L	4.03GB
llama-3-8b-it-kor-extented-chang.IQ4_XS.gguf	IQ4_XS	4.18GB
llama-3-8b-it-kor-extented-chang.Q4_0.gguf	Q4_0	4.34GB
llama-3-8b-it-kor-extented-chang.IQ4_NL.gguf	IQ4_NL	4.38GB
llama-3-8b-it-kor-extented-chang.Q4_K_S.gguf	Q4_K_S	4.37GB
llama-3-8b-it-kor-extented-chang.Q4_K.gguf	Q4_K	4.58GB
llama-3-8b-it-kor-extented-chang.Q4_K_M.gguf	Q4_K_M	4.58GB
llama-3-8b-it-kor-extented-chang.Q4_1.gguf	Q4_1	4.78GB
llama-3-8b-it-kor-extented-chang.Q5_0.gguf	Q5_0	5.21GB
llama-3-8b-it-kor-extented-chang.Q5_K_S.gguf	Q5_K_S	5.21GB
llama-3-8b-it-kor-extented-chang.Q5_K.gguf	Q5_K	5.34GB
llama-3-8b-it-kor-extented-chang.Q5_K_M.gguf	Q5_K_M	5.34GB
llama-3-8b-it-kor-extented-chang.Q5_1.gguf	Q5_1	5.65GB
llama-3-8b-it-kor-extented-chang.Q6_K.gguf	Q6_K	6.14GB
llama-3-8b-it-kor-extented-chang.Q8_0.gguf	Q8_0	7.95GB

Original model description:

library_name: transformers license: apache-2.0 language: - ko

Model Card for Model ID

Model Details

Model Description

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

Chat template

tokenizer.apply_chat_template(chat, tokenize=False)