Patrick von Platen 29f49cd6e3

[Model] Allow loading from original Mistral format (#8168) ...

Co-authored-by: Michael Goin <michael@neuralmagic.com>

2024-09-06 17:02:05 -06:00

..

configs

[BugFix] Fix Granite model configuration (#8216)

2024-09-06 11:39:29 +08:00

tokenizer_group

[mypy] Misc. typing improvements (#7417)

2024-08-13 09:20:20 +08:00

tokenizers

[Frontend] Multimodal support in offline chat (#8098)

2024-09-04 05:22:17 +00:00

__init__.py

[Tokenizer] Add an option to specify tokenizer (#284)

2023-06-28 09:46:58 -07:00

config.py

[Model] Allow loading from original Mistral format (#8168)

2024-09-06 17:02:05 -06:00

detokenizer.py

[Model] Add Mistral Tokenization to improve robustness and chat encoding (#7739)

2024-08-27 12:40:02 +00:00

image_processor.py

[Core] Dynamic image size support for VLMs (#5276)

2024-07-02 20:34:00 -07:00

tokenizer.py

[Core][Bugfix] Accept GGUF model without .gguf extension (#8056)

2024-09-02 08:43:26 -04:00

utils.py

[Core][Bugfix] Accept GGUF model without .gguf extension (#8056)

2024-09-02 08:43:26 -04:00