Phi-3-mini-4k-instruct-onnx / directml /directml-int4-awq-block-128

Commit History

fix(root): Also fixes the tokenizer.json to prevent mismatches.
3b2618a

Gustavo de Rosa commited on

fix(tokenizer_config): Adjusts rstrip of special tokens.
c923b47

Gustavo de Rosa commited on

Add files for Hugging Face's Optimum
4ca7e6e

kvaishnavi commited on

fix(root): Replaces system by user to improve generation experience.
62bd118

gugarosa commited on

fix(genai_config): Adds extra EOS token to improve chat outputs.
27c026f

gugarosa commited on

Upload Phi-3-mini-4k-instruct ONNX models
b33333f

kvaishnavi commited on