bigquant
/

Senku-70B-GPTQ-4bit

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Edit model card

A quantized version of Shinoji Research's Senku 70B Full. Quantized through GPTQ:

Quantization settings:

4bits-128g-desc_act_True-damp_0.01

Downloads last month: 1