Lm-format-enforcer

Latest version: v0.10.9

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

Scan your dependencies

Page 1 of 7

0.10.9

- Added new sample: [Extracting structured data from vision models](https://github.com/noamgat/lm-format-enforcer/blob/main/samples/colab_llama32_vision_enforcer.ipynb)

0.10.8

- Fixed support for tokenizers with larger vocabularies than the models. Enables visual models such as Llama3.2
- JsonSchemaParser: Fixed additionalProperies and oneOf edge cases

0.10.7

- [135] Updated Haystack V2 integration with latest API

0.10.6

- Pickling improvements for easier multiprocessing support

0.10.5

- SequenceParser performance optimization
- JsonSchemaParser: number parsing supports exponents
- Supporting tokenizers with multiple eos token ids

0.10.4

- Added default max Json array length to help LLMs avoid infinite loops. See README for details.
- Updated EXLlamaV2 example to updated API

Page 1 of 7

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.