llama.cpp

mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-04-19 21:16:06 +00:00

History

llama : Add support for DeepSeek V3 (#11049 )

* convert : extend DEEPSEEK2 model architecture to support DeepseekV3ForCausalLM by adding EXPERT_WEIGHTS_NORM and EXPERT_GATING_FUNC model parameters and FFN_EXP_PROBS_B tensor type

* vocab : add DeepSeek V3 pre-tokenizer regexes

* unicode : handle ACCENT_MARK and SYMBOL categories in regex

* llama : add DeepSeek V3 chat template, handle new model parameters and tensor types

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>

2025-01-04 21:06:11 +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

llama : Add support for DeepSeek V3 (#11049 )

2025-01-04 21:06:11 +01:00

gguf_reader.py

gguf-py : numpy 2 newbyteorder fix (#9772 )

2024-12-13 16:48:44 +02:00

gguf_writer.py

llama : Add support for DeepSeek V3 (#11049 )