Commit History

Upload optimized CPU ONNX models

882b7ff

kvaishnavi commited on May 19, 2024

fix(cpu-int4-rtn-block-32): Fixes "(" typo.

791e509
verified

gugarosa commited on May 9, 2024

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

e85d1b3

Gustavo de Rosa commited on May 2, 2024

fix(tokenizer_config): Adjusts rstrip of special tokens.

1d11596

Gustavo de Rosa commited on May 2, 2024

fix(root): Disables inference API since it is not supported for ONNX.

cb44c71
verified

gugarosa commited on May 2, 2024

Add files for Hugging Face's Optimum

f194e0a

kvaishnavi commited on Apr 30, 2024

Increase RC version

bcdf0b0

kvaishnavi commited on Apr 29, 2024

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

66cbe1f

gugarosa commited on Apr 29, 2024

Add config.json for tracking downloads

588e367
verified

kvaishnavi commited on Apr 27, 2024

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

85f5185

gugarosa commited on Apr 26, 2024

Upload Phi-3-mini-128k-instruct ONNX models

fc3f38a

kvaishnavi commited on Apr 23, 2024

initial commit

213ff61
verified

kvaishnavi commited on Apr 23, 2024

Commit History

Upload optimized CPU ONNX models 882b7ff

fix(cpu-int4-rtn-block-32): Fixes "(" typo. 791e509 verified

fix(root): Also fixes the tokenizer.json to prevent mismatches. e85d1b3

fix(tokenizer_config): Adjusts rstrip of special tokens. 1d11596

fix(root): Disables inference API since it is not supported for ONNX. cb44c71 verified

Add files for Hugging Face's Optimum f194e0a

Increase RC version bcdf0b0

fix(root): Replaces system by user to improve generation experience. 66cbe1f

Add config.json for tracking downloads 588e367 verified

fix(genai_config): Adds extra EOS token to improve chat outputs. 85f5185

Upload Phi-3-mini-128k-instruct ONNX models fc3f38a

initial commit 213ff61 verified