Lm-polygraph

Latest version: v0.4.0

Safety actively analyzes 681812 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

0.4.0

Release with a pip package

What's Changed
* Added BLEU metric by ArtemVazh in https://github.com/IINemo/lm-polygraph/pull/213
* New model loading scripts by rvashurin in https://github.com/IINemo/lm-polygraph/pull/211
* Claim-level evaluation for Chinese and Arabic languages by alfekka and ruixing76
* Instruct-tuned models support and reflexive methods by rvashurin in https://github.com/IINemo/lm-polygraph/pull/221
* Blackbox models support via OpenAI API by yobeen in https://github.com/IINemo/lm-polygraph/pull/228
* Rejection rate limit for PRR calculation by ArtemVazh in https://github.com/IINemo/lm-polygraph/pull/230


**Full Changelog**: https://github.com/IINemo/lm-polygraph/compare/v0.3.0..v0.4.0

0.3.0

Release with a pip package

What's Changed
* updated configs for gsm8k by ArtemVazh in https://github.com/IINemo/lm-polygraph/pull/194
* Fix entropy calculation by rvashurin in https://github.com/IINemo/lm-polygraph/pull/197
* Fix gsm8k config by ArtemVazh in https://github.com/IINemo/lm-polygraph/pull/196
* Claim level by cant-access-rediska0123 in https://github.com/IINemo/lm-polygraph/pull/192
* Fix claims extraction by cant-access-rediska0123 in https://github.com/IINemo/lm-polygraph/pull/203
* OpenAI chat try-except added, prompt fixed by Aktsvigun in https://github.com/IINemo/lm-polygraph/pull/204
* Fix warning by rvashurin in https://github.com/IINemo/lm-polygraph/pull/205
* Automatic publish to PyPI when creating new release by SpeedOfMagic in https://github.com/IINemo/lm-polygraph/pull/209
* Monotonic calibration by rvashurin in https://github.com/IINemo/lm-polygraph/pull/199


**Full Changelog**: https://github.com/IINemo/lm-polygraph/compare/v0.2.2...v0.3.0

Links

Releases

Has known vulnerabilities

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.