neuralmagic
/

Phi-3-small-128k-instruct-quantized.w8a16

Text Generation

Model card Files Files and versions Community

Phi-3-small-128k-instruct-quantized.w8a16 / triton_blocksparse_attention_layer.py

Commit History

Upload folder using huggingface_hub

e36a076
verified

alexmarques commited on Aug 15