CoolFace
Modelpublic

RichardErkhov/hchung1017_-_linear-merge-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes98downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

linear-merge - GGUF

  • —Model creator: https://huggingface.co/hchung1017/
  • —Original model: https://huggingface.co/hchung1017/linear-merge/
NameQuant methodSize
linear-merge.Q2_K.ggufQ2_K3.73GB
linear-merge.Q3_K_S.ggufQ3KS4.34GB
linear-merge.Q3_K.ggufQ3_K4.84GB
linear-merge.Q3_K_M.ggufQ3KM4.84GB
linear-merge.Q3_K_L.ggufQ3KL5.26GB
linear-merge.IQ4_XS.ggufIQ4_XS5.43GB
linear-merge.Q4_0.ggufQ4_05.66GB
linear-merge.IQ4_NL.ggufIQ4_NL5.72GB
linear-merge.Q4_K_S.ggufQ4KS5.7GB
linear-merge.Q4_K.ggufQ4_K6.02GB
linear-merge.Q4_K_M.ggufQ4KM6.02GB
linear-merge.Q4_1.ggufQ4_16.27GB
linear-merge.Q5_0.ggufQ5_06.89GB
linear-merge.Q5_K_S.ggufQ5KS6.89GB
linear-merge.Q5_K.ggufQ5_K7.08GB
linear-merge.Q5_K_M.ggufQ5KM7.08GB
linear-merge.Q5_1.ggufQ5_17.51GB
linear-merge.Q6_K.ggufQ6_K8.2GB
linear-merge.Q8_0.ggufQ8_010.62GB

Original model description: --- license: mit ---

Base model is generated by merging LDCC/LDCC-SOLAR-10.7B, hyeogi/SOLAR-10.7B-dpo-v1, and megastudyedu/M-SOLAR-10.7B-v1.3 linearly.

Model Details

  • —Model Developers : hchung1017(hoon chung)
  • —Repository : https://huggingface.co/hchung1017/linear-merge
  • —base mode : LDCC/LDCC-SOLAR-10.7B, hyeogi/SOLAR-10.7B-dpo-v1, and megastudyedu/M-SOLAR-10.7B-v1.3