pipihand01's picture
Update README.md
b04f585 verified
metadata
base_model: princeton-nlp/gemma-2-9b-it-SimPO
tags:
  - alignment-handbook
  - generated_from_trainer
datasets:
  - princeton-nlp/gemma2-ultrafeedback-armorm
model-index:
  - name: princeton-nlp/gemma-2-9b-it-SimPO
    results: []
license:
  - mit
  - gemma
quantized_by: pipihand01

GGUF files of princeton-nlp/gemma-2-9b-it-SimPO.


Files quantized with larger embed and output weights than normal GGUF setting

  • Q8_0 embed and output weights: Q6_K_L, Q5_K_L, Q4_K_L

  • bf16 embed and output weights (maybe slower inference): Q8_0_L, Q6_K_XL, Q5_K_XL, Q4_K_XL