CoolFace
Modelpublic

RichardErkhov/jointpreferences_-_mistral_7b_sft_helpful-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes746downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mistral7bsft_helpful - GGUF

  • —Model creator: https://huggingface.co/jointpreferences/
  • —Original model: https://huggingface.co/jointpreferences/mistral7bsft_helpful/
NameQuant methodSize
mistral_7b_sft_helpful.Q2_K.ggufQ2_K2.53GB
mistral_7b_sft_helpful.IQ3_XS.ggufIQ3_XS2.81GB
mistral_7b_sft_helpful.IQ3_S.ggufIQ3_S2.96GB
mistral_7b_sft_helpful.Q3_K_S.ggufQ3KS2.95GB
mistral_7b_sft_helpful.IQ3_M.ggufIQ3_M3.06GB
mistral_7b_sft_helpful.Q3_K.ggufQ3_K3.28GB
mistral_7b_sft_helpful.Q3_K_M.ggufQ3KM3.28GB
mistral_7b_sft_helpful.Q3_K_L.ggufQ3KL3.56GB
mistral_7b_sft_helpful.IQ4_XS.ggufIQ4_XS3.67GB
mistral_7b_sft_helpful.Q4_0.ggufQ4_03.83GB
mistral_7b_sft_helpful.IQ4_NL.ggufIQ4_NL3.87GB
mistral_7b_sft_helpful.Q4_K_S.ggufQ4KS3.86GB
mistral_7b_sft_helpful.Q4_K.ggufQ4_K4.07GB
mistral_7b_sft_helpful.Q4_K_M.ggufQ4KM4.07GB
mistral_7b_sft_helpful.Q4_1.ggufQ4_14.24GB
mistral_7b_sft_helpful.Q5_0.ggufQ5_04.65GB
mistral_7b_sft_helpful.Q5_K_S.ggufQ5KS4.65GB
mistral_7b_sft_helpful.Q5_K.ggufQ5_K4.78GB
mistral_7b_sft_helpful.Q5_K_M.ggufQ5KM4.78GB
mistral_7b_sft_helpful.Q5_1.ggufQ5_15.07GB
mistral_7b_sft_helpful.Q6_K.ggufQ6_K5.53GB
mistral_7b_sft_helpful.Q8_0.ggufQ8_07.17GB

Original model description: Paper: Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization

Link: https://arxiv.org/abs/2404.00530

Github: https://github.com/Hritikbansal/dove