neuralmagic
/

Meta-Llama-3-70B-Instruct-quantized.w8a8

Text Generation

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Meta-Llama-3-70B-Instruct-quantized.w8a8

Commit History

initial commit

3633bf7
verified

alexmarques commited on Jul 14, 2024