You can deploy this model and start earning money today!

RichardErkhov/
princeton-nlp_-_Mistral-7B-Base-SFT-IPO-gguf

Name: princeton-nlp_-_Mistral-7B-Base-SFT-IPO-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-7B-Base-SFT-IPO - GGUF

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

Name	Quant method	Size
Mistral-7B-Base-SFT-IPO.Q2_K.gguf	Q2_K	2.53GB
Mistral-7B-Base-SFT-IPO.IQ3_XS.gguf	IQ3_XS	2.29GB
Mistral-7B-Base-SFT-IPO.IQ3_S.gguf	IQ3_S	1.07GB
Mistral-7B-Base-SFT-IPO.Q3_K_S.gguf	Q3_K_S	2.95GB
Mistral-7B-Base-SFT-IPO.IQ3_M.gguf	IQ3_M	3.06GB
Mistral-7B-Base-SFT-IPO.Q3_K.gguf	Q3_K	3.28GB
Mistral-7B-Base-SFT-IPO.Q3_K_M.gguf	Q3_K_M	3.28GB
Mistral-7B-Base-SFT-IPO.Q3_K_L.gguf	Q3_K_L	0.34GB
Mistral-7B-Base-SFT-IPO.IQ4_XS.gguf	IQ4_XS	3.67GB
Mistral-7B-Base-SFT-IPO.Q4_0.gguf	Q4_0	3.83GB
Mistral-7B-Base-SFT-IPO.IQ4_NL.gguf	IQ4_NL	3.87GB
Mistral-7B-Base-SFT-IPO.Q4_K_S.gguf	Q4_K_S	3.86GB
Mistral-7B-Base-SFT-IPO.Q4_K.gguf	Q4_K	4.07GB
Mistral-7B-Base-SFT-IPO.Q4_K_M.gguf	Q4_K_M	4.07GB
Mistral-7B-Base-SFT-IPO.Q4_1.gguf	Q4_1	4.24GB
Mistral-7B-Base-SFT-IPO.Q5_0.gguf	Q5_0	4.65GB
Mistral-7B-Base-SFT-IPO.Q5_K_S.gguf	Q5_K_S	4.65GB
Mistral-7B-Base-SFT-IPO.Q5_K.gguf	Q5_K	4.78GB
Mistral-7B-Base-SFT-IPO.Q5_K_M.gguf	Q5_K_M	4.78GB
Mistral-7B-Base-SFT-IPO.Q5_1.gguf	Q5_1	5.07GB
Mistral-7B-Base-SFT-IPO.Q6_K.gguf	Q6_K	5.53GB
Mistral-7B-Base-SFT-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 Please refer to our repository for more details.

RichardErkhov/princeton-nlp_-_Mistral-7B-Base-SFT-IPO-gguf

RichardErkhov/
princeton-nlp_-_Mistral-7B-Base-SFT-IPO-gguf