compressa-ai
/

Llama-3-8B-Instruct-OmniQuant

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

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

Vasily Alexeev

add asymm quantized model, add two eos in code sample

6758e8a 7 months ago

history blame contribute delete

64 Bytes

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