compressa-ai
/

Saiga-Llama-3-8B-OmniQuant

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Saiga-Llama-3-8B-OmniQuant / quant_config.json

Vasily Alexeev

add weights and stuff

2c038a7 7 months ago

history blame contribute delete

63 Bytes

{"wbits": 4, "abits": 16, "group_size": 128, "symmetric": true}