Francis Couture-Harpin 95930da30e convert-hf : get bit-exact same output as ./quantize ... The quantization version was missing. * convert-hf : don't round bf16 NANs * convert-hf : save some memory with np.int16 intermediate bf16 weights * convert-hf : more closely match llama.cpp with which weights to keep in f32		2024-05-09 12:29:31 -04:00
..
__init__.py	convert-hf : support bfloat16 conversion	2024-05-08 23:14:25 -04:00
constants.py	convert-hf : get bit-exact same output as ./quantize	2024-05-09 12:29:31 -04:00
gguf.py	gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)	2023-11-11 08:04:50 +03:00
gguf_reader.py	convert-hf : save memory with lazy evaluation (#7075)	2024-05-08 18:16:38 -04:00
gguf_writer.py	convert-hf : get bit-exact same output as ./quantize	2024-05-09 12:29:31 -04:00
lazy.py	gguf-py : flake8 fixes	2024-05-08 23:21:13 -04:00
py.typed	convert : various script cleanups/fixes + merges and special token handling (#2842)	2023-08-30 11:25:50 +03:00
tensor_mapping.py	llama : add phi3 support (#6852)	2024-04-24 10:00:37 +03:00
vocab.py	convert-hf : save memory with lazy evaluation (#7075)	2024-05-08 18:16:38 -04:00