Modelpublic

RichardErkhov/We-Want-GPU_-_Yi-Ko-6B-orca-alpaca-gpt4-math-lora-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes679downloads

Model Card

Quantization made by Richard Erkhov.

Yi-Ko-6B-orca-alpaca-gpt4-math-lora - GGUF

—Model creator: https://huggingface.co/We-Want-GPU/
—Original model: https://huggingface.co/We-Want-GPU/Yi-Ko-6B-orca-alpaca-gpt4-math-lora/

Name	Quant method	Size
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q2_K.gguf	Q2_K	2.24GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.IQ3_XS.gguf	IQ3_XS	2.48GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.IQ3_S.gguf	IQ3_S	2.6GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q3_K_S.gguf	Q3KS	2.59GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.IQ3_M.gguf	IQ3_M	2.69GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q3_K.gguf	Q3_K	2.86GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q3_K_M.gguf	Q3KM	2.86GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q3_K_L.gguf	Q3KL	3.08GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.IQ4_XS.gguf	IQ4_XS	3.18GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q4_0.gguf	Q4_0	3.32GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.IQ4_NL.gguf	IQ4_NL	3.35GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q4_K_S.gguf	Q4KS	3.34GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q4_K.gguf	Q4_K	3.5GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q4_K_M.gguf	Q4KM	3.5GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q4_1.gguf	Q4_1	3.66GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q5_0.gguf	Q5_0	4.0GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q5_K_S.gguf	Q5KS	4.0GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q5_K.gguf	Q5_K	4.09GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q5_K_M.gguf	Q5KM	4.09GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q5_1.gguf	Q5_1	4.34GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q6_K.gguf	Q6_K	4.72GB
Yi-Ko-6B-orca-alpaca-gpt4-math-lora.Q8_0.gguf	Q8_0	6.12GB

Original model description: Entry not found