| .. |
|
scripts
|
4fcd87cf7c
gguf-py : skip endian-conversion of MXFP4 data (#17523)
|
1 mesiac pred |
|
__init__.py
|
672a6f1018
convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499)
|
1 rok pred |
|
constants.py
|
ff55414c42
model : Qwen3 Next (#16095)
|
1 mesiac pred |
|
gguf.py
|
34b0a08207
gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)
|
2 rokov pred |
|
gguf_reader.py
|
eb0f5c28d3
gguf-py : display the invalid gguf type (#13687)
|
8 mesiacov pred |
|
gguf_writer.py
|
05872ac885
convert : fix big-endian conversion (#17431)
|
1 mesiac pred |
|
lazy.py
|
1c07c0c68c
convert : handle compressed-tensors quant method (#17069)
|
2 mesiacov pred |
|
metadata.py
|
877566d512
llama: introduce support for model-embedded sampling parameters (#17120)
|
1 mesiac pred |
|
py.typed
|
dc07dc492e
convert : various script cleanups/fixes + merges and special token handling (#2842)
|
2 rokov pred |
|
quants.py
|
e54d41befc
gguf-py : add Numpy MXFP4 de/quantization support (#15111)
|
5 mesiacov pred |
|
tensor_mapping.py
|
ff55414c42
model : Qwen3 Next (#16095)
|
1 mesiac pred |
|
utility.py
|
802cef44bf
convert : parse safetensors directly (#15667)
|
2 mesiacov pred |
|
vocab.py
|
dd62dcfab9
convert : Make mistral-common dependency optional (#16738)
|
2 mesiacov pred |
Piotr Wilkin (ilintar)
ff55414c42
model : Qwen3 Next (#16095)