vietan32/facebook-xml-roberta-base-300k-gg-snippets-bnb-4bit
017
vietan32/facebook-xml-roberta-base-300k-gg-snippets (Quantized)
Description
This model is a quantized version of the original model `vietan32/facebook-xml-roberta-base-300k-gg-snippets`.
It's quantized using the BitsAndBytes library to 4-bit using the bnb-my-repo space.
Quantization Details
- Quantization Type: int4
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
- bnb_4bit_quant_storage: uint8
