Modelpublic

RichardErkhov/openthaigpt_-_openthai-llama-pretrained-7B-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes4.1kdownloads

Model Card

Quantization made by Richard Erkhov.

openthai-llama-pretrained-7B - GGUF

—Model creator: https://huggingface.co/openthaigpt/
—Original model: https://huggingface.co/openthaigpt/openthai-llama-pretrained-7B/

Name	Quant method	Size
openthai-llama-pretrained-7B.Q2_K.gguf	Q2_K	2.47GB
openthai-llama-pretrained-7B.IQ3_XS.gguf	IQ3_XS	2.72GB
openthai-llama-pretrained-7B.IQ3_S.gguf	IQ3_S	2.86GB
openthai-llama-pretrained-7B.Q3_K_S.gguf	Q3KS	2.86GB
openthai-llama-pretrained-7B.IQ3_M.gguf	IQ3_M	3.02GB
openthai-llama-pretrained-7B.Q3_K.gguf	Q3_K	3.19GB
openthai-llama-pretrained-7B.Q3_K_M.gguf	Q3KM	3.19GB
openthai-llama-pretrained-7B.Q3_K_L.gguf	Q3KL	3.47GB
openthai-llama-pretrained-7B.IQ4_XS.gguf	IQ4_XS	3.52GB
openthai-llama-pretrained-7B.Q4_0.gguf	Q4_0	3.69GB
openthai-llama-pretrained-7B.IQ4_NL.gguf	IQ4_NL	3.71GB
openthai-llama-pretrained-7B.Q4_K_S.gguf	Q4KS	3.72GB
openthai-llama-pretrained-7B.Q4_K.gguf	Q4_K	3.93GB
openthai-llama-pretrained-7B.Q4_K_M.gguf	Q4KM	3.93GB
openthai-llama-pretrained-7B.Q4_1.gguf	Q4_1	4.08GB
openthai-llama-pretrained-7B.Q5_0.gguf	Q5_0	4.47GB
openthai-llama-pretrained-7B.Q5_K_S.gguf	Q5KS	4.47GB
openthai-llama-pretrained-7B.Q5_K.gguf	Q5_K	4.6GB
openthai-llama-pretrained-7B.Q5_K_M.gguf	Q5KM	4.6GB
openthai-llama-pretrained-7B.Q5_1.gguf	Q5_1	4.86GB
openthai-llama-pretrained-7B.Q6_K.gguf	Q6_K	5.3GB
openthai-llama-pretrained-7B.Q8_0.gguf	Q8_0	6.87GB

Original model description: Entry not found