neural-nova
/

Mistral-7B-Instruct-v0.3-optimized

inference-optimization

Model card Files Files and versions

Mistral-7B-Instruct-v0.3-optimized / kernels /MistralMLP

Commit History

Add optimized Mistral-7B-Instruct-v0.3 build (MistralRMSNorm + MistralMLP CUDA kernels)

e57527b
verified

Khanin Udomchoksakul commited on 4 days ago