metadata
base_model:
- medmekk/eter3
medmekk/eter3 (Quantized)
Description
This model is a quantized version of the original model medmekk/eter3. It has been quantized using int4 quantization with bitsandbytes.
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: int8
Usage
You can use this model in your applications by loading it directly from the Hugging Face Hub:
from transformers import AutoModel
model = AutoModel.from_pretrained("medmekk/eter3")