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

Downloads last month
63
GGUF
Model size
9.24B params
Architecture
gemma2
Hardware compatibility
Log In to view the estimation

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for pipihand01/gemma-2-9b-it-SimPO-GGUF

Base model

google/gemma-2-9b
Quantized
(36)
this model

Dataset used to train pipihand01/gemma-2-9b-it-SimPO-GGUF