RichardErkhov/lcw99_-_llama-3-10b-wiki-240709-f-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3-10b-wiki-240709-f - GGUF

• Model creator: https://huggingface.co/lcw99/
• Original model: https://huggingface.co/lcw99/llama-3-10b-wiki-240709-f/

Name	Quant method	Size
llama-3-10b-wiki-240709-f.Q2_K.gguf	Q2_K	3.56GB
llama-3-10b-wiki-240709-f.IQ3_XS.gguf	IQ3_XS	3.94GB
llama-3-10b-wiki-240709-f.IQ3_S.gguf	IQ3_S	4.13GB
llama-3-10b-wiki-240709-f.Q3_K_S.gguf	Q3_K_S	4.11GB
llama-3-10b-wiki-240709-f.IQ3_M.gguf	IQ3_M	4.25GB
llama-3-10b-wiki-240709-f.Q3_K.gguf	Q3_K	4.52GB
llama-3-10b-wiki-240709-f.Q3_K_M.gguf	Q3_K_M	4.52GB
llama-3-10b-wiki-240709-f.Q3_K_L.gguf	Q3_K_L	4.88GB
llama-3-10b-wiki-240709-f.IQ4_XS.gguf	IQ4_XS	5.05GB
llama-3-10b-wiki-240709-f.Q4_0.gguf	Q4_0	5.26GB
llama-3-10b-wiki-240709-f.IQ4_NL.gguf	IQ4_NL	5.31GB
llama-3-10b-wiki-240709-f.Q4_K_S.gguf	Q4_K_S	5.29GB
llama-3-10b-wiki-240709-f.Q4_K.gguf	Q4_K	5.56GB
llama-3-10b-wiki-240709-f.Q4_K_M.gguf	Q4_K_M	5.56GB
llama-3-10b-wiki-240709-f.Q4_1.gguf	Q4_1	5.79GB
llama-3-10b-wiki-240709-f.Q5_0.gguf	Q5_0	6.33GB
llama-3-10b-wiki-240709-f.Q5_K_S.gguf	Q5_K_S	6.33GB
llama-3-10b-wiki-240709-f.Q5_K.gguf	Q5_K	6.49GB
llama-3-10b-wiki-240709-f.Q5_K_M.gguf	Q5_K_M	6.49GB
llama-3-10b-wiki-240709-f.Q5_1.gguf	Q5_1	6.87GB
llama-3-10b-wiki-240709-f.Q6_K.gguf	Q6_K	7.48GB
llama-3-10b-wiki-240709-f.Q8_0.gguf	Q8_0	9.68GB

Original model description:

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

Model Card for Model ID

Model Details

Model Description

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

Chat template

tokenizer.apply_chat_template(chat, tokenize=False)