cturan/llama.cpp @ d46dbc76f8770caec0175f1e57777173c70556a0

compilade f98eb31c51 convert-hf : save memory with lazy evaluation (#7075)		1 年之前
..
__init__.py	34b0a08207 gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)	2 年之前
constants.py	f98eb31c51 convert-hf : save memory with lazy evaluation (#7075)	1 年之前
gguf.py	34b0a08207 gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)	2 年之前
gguf_reader.py	f98eb31c51 convert-hf : save memory with lazy evaluation (#7075)	1 年之前
gguf_writer.py	f98eb31c51 convert-hf : save memory with lazy evaluation (#7075)	1 年之前
py.typed	dc07dc492e convert : various script cleanups/fixes + merges and special token handling (#2842)	2 年之前
tensor_mapping.py	c8297c6af5 llama : add phi3 support (#6852)	1 年之前
vocab.py	f98eb31c51 convert-hf : save memory with lazy evaluation (#7075)	1 年之前