Lm-format-enforcer

Latest version: v0.10.2

Safety actively analyzes 638755 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 2 of 6

0.9.6

- [88] ExllamaV2 optimizations
- Bugfix in ExllamaV2 sample notebook that generated garbage data after the response.

0.9.5

- [87] Allow regex to exit to forcestopparser when receiving a pad/eos token after having been in a final state. Thanks Josh C!

0.9.4

- [27] Improving vLLM class support (AsyncLLMEngine etc)

0.9.3

- [83](https://github.com/noamgat/lm-format-enforcer/pull/83) - Supporting added model tokens
- Improved support for out-of-token-vocabulary characters

0.9.2

- [80](https://github.com/noamgat/lm-format-enforcer/issues/80) - Fixed bug where comma could start json list
- [34](https://github.com/noamgat/lm-format-enforcer/issues/34) - Fixed llama-cpp-python low max_tokens default in sample

0.9.1

- Fixed build errors in certain edge cases

Page 2 of 6

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.