| .. |
|
__init__.py
|
672a6f1018
convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499)
|
преди 1 година |
|
constants.py
|
62e84d9848
llama : add 128k yarn context for Qwen (#10698)
|
преди 1 година |
|
gguf.py
|
34b0a08207
gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)
|
преди 2 години |
|
gguf_reader.py
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
преди 1 година |
|
gguf_writer.py
|
a0ec17b32e
metadata: Detailed Dataset Authorship Metadata (#8875)
|
преди 1 година |
|
lazy.py
|
3a14e00366
gguf-py : simplify support for quant types (#8838)
|
преди 1 година |
|
metadata.py
|
96fa2c5e2d
fix gguf-py: Conversion error when multiple licenses are configured (#9807)
|
преди 1 година |
|
py.typed
|
dc07dc492e
convert : various script cleanups/fixes + merges and special token handling (#2842)
|
преди 2 години |
|
quants.py
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
преди 1 година |
|
tensor_mapping.py
|
c5ede3849f
convert : add custom attention mapping
|
преди 1 година |
|
utility.py
|
328884f421
gguf-py : fix some metadata name extraction edge cases (#8591)
|
преди 1 година |
|
vocab.py
|
e3c355ba65
convert : handle tokenizer merges format from transformers 4.45 (#9696)
|
преди 1 година |
Robert Collins
62e84d9848
llama : add 128k yarn context for Qwen (#10698)