Modelpublic

RichardErkhov/princeton-nlp_-_Mistral-7B-Instruct-IPO-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes518downloads

Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-7B-Instruct-IPO - GGUF

—Model creator: https://huggingface.co/princeton-nlp/
—Original model: https://huggingface.co/princeton-nlp/Mistral-7B-Instruct-IPO/

Name	Quant method	Size
Mistral-7B-Instruct-IPO.Q2_K.gguf	Q2_K	2.53GB
Mistral-7B-Instruct-IPO.IQ3_XS.gguf	IQ3_XS	2.81GB
Mistral-7B-Instruct-IPO.IQ3_S.gguf	IQ3_S	2.96GB
Mistral-7B-Instruct-IPO.Q3_K_S.gguf	Q3KS	2.95GB
Mistral-7B-Instruct-IPO.IQ3_M.gguf	IQ3_M	3.06GB
Mistral-7B-Instruct-IPO.Q3_K.gguf	Q3_K	3.28GB
Mistral-7B-Instruct-IPO.Q3_K_M.gguf	Q3KM	3.28GB
Mistral-7B-Instruct-IPO.Q3_K_L.gguf	Q3KL	3.56GB
Mistral-7B-Instruct-IPO.IQ4_XS.gguf	IQ4_XS	3.67GB
Mistral-7B-Instruct-IPO.Q4_0.gguf	Q4_0	3.83GB
Mistral-7B-Instruct-IPO.IQ4_NL.gguf	IQ4_NL	3.87GB
Mistral-7B-Instruct-IPO.Q4_K_S.gguf	Q4KS	3.86GB
Mistral-7B-Instruct-IPO.Q4_K.gguf	Q4_K	4.07GB
Mistral-7B-Instruct-IPO.Q4_K_M.gguf	Q4KM	4.07GB
Mistral-7B-Instruct-IPO.Q4_1.gguf	Q4_1	4.24GB
Mistral-7B-Instruct-IPO.Q5_0.gguf	Q5_0	4.65GB
Mistral-7B-Instruct-IPO.Q5_K_S.gguf	Q5KS	4.65GB
Mistral-7B-Instruct-IPO.Q5_K.gguf	Q5_K	4.78GB
Mistral-7B-Instruct-IPO.Q5_K_M.gguf	Q5KM	4.78GB
Mistral-7B-Instruct-IPO.Q5_1.gguf	Q5_1	5.07GB
Mistral-7B-Instruct-IPO.Q6_K.gguf	Q6_K	5.53GB
Mistral-7B-Instruct-IPO.Q8_0.gguf	Q8_0	7.17GB

Original model description: This is a model released from the preprint: [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://arxiv.org/abs/2405.14734) Please refer to our repository for more details.