ranjan56cse
/

gpt2-large-agnews-quantization-bitsandbytes

Text Classification

Model card Files Files and versions

GPT-2 Large AG News - bitsandbytes Quantization Results

Quantization results using bitsandbytes library.

Methods

INT8 (8-bit)
NF4 (4-bit)

Results

See task_2_3_results.json for complete metrics.

Base model: ranjan56cse/gpt2-large-agnews-classifier

Downloads last month: -; Downloads are not tracked for this model. How to track