CoolFace
Modelpublic

RichardErkhov/PolyAgent_-_gemma-7b-custom-tokenizer-base-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes999downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-7b-custom-tokenizer-base - GGUF

  • —Model creator: https://huggingface.co/PolyAgent/
  • —Original model: https://huggingface.co/PolyAgent/gemma-7b-custom-tokenizer-base/
NameQuant methodSize
gemma-7b-custom-tokenizer-base.Q2_K.ggufQ2_K3.24GB
gemma-7b-custom-tokenizer-base.IQ3_XS.ggufIQ3_XS3.54GB
gemma-7b-custom-tokenizer-base.IQ3_S.ggufIQ3_S3.71GB
gemma-7b-custom-tokenizer-base.Q3_K_S.ggufQ3KS3.71GB
gemma-7b-custom-tokenizer-base.IQ3_M.ggufIQ3_M3.82GB
gemma-7b-custom-tokenizer-base.Q3_K.ggufQ3_K4.07GB
gemma-7b-custom-tokenizer-base.Q3_K_M.ggufQ3KM4.07GB
gemma-7b-custom-tokenizer-base.Q3_K_L.ggufQ3KL4.39GB
gemma-7b-custom-tokenizer-base.IQ4_XS.ggufIQ4_XS4.48GB
gemma-7b-custom-tokenizer-base.Q4_0.ggufQ4_04.67GB
gemma-7b-custom-tokenizer-base.IQ4_NL.ggufIQ4_NL4.69GB
gemma-7b-custom-tokenizer-base.Q4_K_S.ggufQ4KS4.7GB
gemma-7b-custom-tokenizer-base.Q4_K.ggufQ4_K4.96GB
gemma-7b-custom-tokenizer-base.Q4_K_M.ggufQ4KM4.96GB
gemma-7b-custom-tokenizer-base.Q4_1.ggufQ4_15.12GB
gemma-7b-custom-tokenizer-base.Q5_0.ggufQ5_05.57GB
gemma-7b-custom-tokenizer-base.Q5_K_S.ggufQ5KS5.57GB
gemma-7b-custom-tokenizer-base.Q5_K.ggufQ5_K5.72GB
gemma-7b-custom-tokenizer-base.Q5_K_M.ggufQ5KM5.72GB
gemma-7b-custom-tokenizer-base.Q5_1.ggufQ5_16.02GB
gemma-7b-custom-tokenizer-base.Q6_K.ggufQ6_K6.53GB
gemma-7b-custom-tokenizer-base.Q8_0.ggufQ8_08.45GB

Original model description: --- license: gemma ---

Model uses the correct gemmauaordered.model tokenizer as of July 20th 2024.