| .. |
|
scripts
|
a7366faa5b
gguf-py : avoid requiring pyside6 for other scripts (#13036)
|
vor 9 Monaten |
|
__init__.py
|
672a6f1018
convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499)
|
vor 1 Jahr |
|
constants.py
|
2f567611c0
llama-model : support Qwen2 embedding models and pooling_mode_lasttoken (#13245)
|
vor 9 Monaten |
|
gguf.py
|
34b0a08207
gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)
|
vor 2 Jahren |
|
gguf_reader.py
|
69050a11be
Refactor gguf scripts to improve metadata handling (#11909)
|
vor 11 Monaten |
|
gguf_writer.py
|
074e42ab31
convert : converting mmproj for Qwen2/2.5VL from convert_hf_to_gguf (#13209)
|
vor 9 Monaten |
|
lazy.py
|
a226bc7a9a
gguf-py : support lazy tensor splitting (#12809)
|
vor 10 Monaten |
|
metadata.py
|
06c2b1561d
convert : fix Norway problem when parsing YAML (#12114)
|
vor 11 Monaten |
|
py.typed
|
dc07dc492e
convert : various script cleanups/fixes + merges and special token handling (#2842)
|
vor 2 Jahren |
|
quants.py
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
vor 1 Jahr |
|
tensor_mapping.py
|
5215b91e93
clip : fix confused naming ffn_up and ffn_down (#13290)
|
vor 9 Monaten |
|
utility.py
|
64eda5deb9
convert : ability to lazy-load safetensors remotely without downloading to disk (#12820)
|
vor 9 Monaten |
|
vocab.py
|
a686171ea7
convert : Support chat_template.json (#12460)
|
vor 10 Monaten |
compilade
a7366faa5b
gguf-py : avoid requiring pyside6 for other scripts (#13036)