Xuan-Son Nguyen 7798007a29 mtmd: support DeepSeek-V4-Flash-Vision-Exp (#28133) ...

* mtmd: support DeepSeek-V4-Flash-Vision-Exp

* handle min/max token counts from CLI

* rm debugging

* use GGML_ROPE_TYPE_VISION

* nits

* apply review comments

* correct token count

2026-09-02 16:43:43 +02:00

..

scripts

convert: Add endianness conversion for Q1 and TQ2 quantizations (#26618)

2026-08-05 18:06:09 +08:00

__init__.py

convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499)

2024-07-18 20:40:15 +10:00

constants.py

mtmd: support DeepSeek-V4-Flash-Vision-Exp (#28133)

2026-09-02 16:43:43 +02:00

gguf_reader.py

gguf-py : add size guards to GGUFReader (#27188)

2026-08-19 09:35:27 +03:00

gguf_writer.py

convert: prevent ndarray conversion in LazyChunkedTensor (#27869)

2026-08-28 11:46:30 +02:00

gguf.py

gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)

2023-11-11 08:04:50 +03:00

lazy.py

convert: prevent ndarray conversion in LazyChunkedTensor (#27869)

2026-08-28 11:46:30 +02:00

metadata.py

misc : read repetition_penalty from generation_config.json (#27659)

2026-08-24 17:01:35 +03:00

py.typed

convert : various script cleanups/fixes + merges and special token handling (#2842)

2023-08-30 11:25:50 +03:00

quants.py

convert : minor fixes for numpy 2.x (#23571)

2026-05-24 09:51:31 +02:00

tensor_mapping.py

mtmd: support DeepSeek-V4-Flash-Vision-Exp (#28133)

2026-09-02 16:43:43 +02:00

utility.py

gguf-py : do not align the data start offset (#18291)

2025-12-22 20:25:16 +01:00

vocab.py

vocab : adopt leading TemplateProcessing special token as BOS (#24428)

2026-06-11 10:37:23 +03:00