BrokenSoul
/

GPT2-GPTQ-4bit

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Edit model card

BrokenSoul/GPT2-GPTQ-4bit

This is a GPT2 Quantized model following this tutorial: 4-bit LLM Quantization with GPTQ.

Downloads last month: 0