llama.cpp/gguf-py/gguf
Xuan-Son Nguyen 3d86c6c2b5
model: support GLM4V vision encoder (#18042)
* convert ok

* no deepstack

* less new tensors

* cgraph ok

* add mrope for text model

* faster patch merger

* add GGML_ROPE_TYPE_MRNORM

* add support for metal

* move glm4v do dedicated graph

* convert: add norm_embd

* clip: add debugging fn

* working correctly

* fix style

* use bicubic

* fix mrope metal

* improve cpu

* convert to neox ordering on conversion

* revert backend changes

* force stop if using old weight

* support moe variant

* fix conversion

* fix convert (2)

* Update tools/mtmd/clip-graph.h

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* process mrope_section on TextModel base class

* resolve conflict merge

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-12-16 11:25:26 +01:00
..
scripts gguf-py : fix passing non-native endian tensors (editor-gui and new-metadata) (#17553) 2025-11-28 20:53:01 +01:00
__init__.py convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499) 2024-07-18 20:40:15 +10:00
constants.py model: support GLM4V vision encoder (#18042) 2025-12-16 11:25:26 +01:00
gguf.py gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981) 2023-11-11 08:04:50 +03:00
gguf_reader.py gguf-py : display the invalid gguf type (#13687) 2025-05-21 16:33:54 +02:00
gguf_writer.py model: support Ministral3 (#17644) 2025-12-01 12:26:52 +01:00
lazy.py convert : handle compressed-tensors quant method (#17069) 2025-11-09 09:45:50 -05:00
metadata.py llama: introduce support for model-embedded sampling parameters (#17120) 2025-11-25 09:56:07 +08:00
py.typed convert : various script cleanups/fixes + merges and special token handling (#2842) 2023-08-30 11:25:50 +03:00
quants.py gguf-py : add Numpy MXFP4 de/quantization support (#15111) 2025-08-08 17:48:26 -04:00
tensor_mapping.py model: support GLM4V vision encoder (#18042) 2025-12-16 11:25:26 +01:00
utility.py convert : parse safetensors directly (#15667) 2025-11-09 09:49:40 -05:00
vocab.py convert : support latest mistral-common (fix conversion with --mistral-format) (#17712) 2025-12-03 21:15:04 +01:00