Hugging Face's logo

medmekk
/
Llama-3.2-1B-BNB-int4-nf4

Safetensors
llama
4-bit precision
bitsandbytes
Model card Files Community
Llama-3.2-1B-BNB-int4-nf4 / README.md
medmekk's picture
medmekk HF staff
Upload folder using huggingface_hub
17bde65 verified
preview code
|
raw
history blame contribute delete
647 Bytes
metadata
base_model:
  - medmekk/Llama-3.2-1B-BNB-int4-nf4

medmekk/Llama-3.2-1B-BNB-int4-nf4 (Quantized)

Description

This model is a quantized version of the original model medmekk/Llama-3.2-1B-BNB-int4-nf4. It has been quantized using int4 quantization with bitsandbytes.

Quantization Details

  • Quantization Type: int4
  • Threshold: None
  • bnb_4bit_quant_type: nf4
  • bnb_4bit_use_double_quant: False

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/Llama-3.2-1B-BNB-int4-nf4")