Francis Couture-Harpin 3a0bf17d57 gguf-py : Numpy (de)quantization for TQ1_0 and TQ2_0 ... * ggml-quants : use roundf instead of nearest_int for TQ1_0 and TQ2_0 This does not change anything for ternary models, since their values should never end up being in halfway cases anyway.		2024-08-12 00:06:48 -04:00
..
__init__.py	convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499)	2024-07-18 20:40:15 +10:00
constants.py	Merge branch 'master' into compilade/bitnet-ternary	2024-08-11 15:52:29 -04:00
gguf_reader.py	py : type-check all Python scripts with Pyright (#8341)	2024-07-07 15:04:39 -04:00
gguf_writer.py	Stop the generation when <|eom_id|> token is encountered - needed for Llama 3.1 tool call support (#8858)	2024-08-05 09:38:01 +02:00
gguf.py	gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)	2023-11-11 08:04:50 +03:00
lazy.py	gguf-py : simplify support for quant types (#8838)	2024-08-08 13:33:09 -04:00
metadata.py	server : add lora hotswap endpoint (WIP) (#8857)	2024-08-06 17:33:39 +02:00
py.typed	convert : various script cleanups/fixes + merges and special token handling (#2842)	2023-08-30 11:25:50 +03:00
quants.py	gguf-py : Numpy (de)quantization for TQ1_0 and TQ2_0	2024-08-12 00:06:48 -04:00
tensor_mapping.py	convert_hf : faster lazy safetensors (#8482)	2024-07-15 23:13:10 -04:00
utility.py	gguf-py : fix some metadata name extraction edge cases (#8591)	2024-07-20 21:58:49 -04:00
vocab.py	Move convert.py to examples/convert-legacy-llama.py (#7430)	2024-05-30 21:40:00 +10:00