llama.cpp
Fix import of llama2.c models that don't share weights between embedding layers
#2685

Merged

Commits

Fix import of llama2.c models that don't share weights between embedding layers

ochafik committed 3 years ago
llama2c: reinstate ggmlv3 conversion output + update readme w/ gguf conv

ochafik committed 3 years ago
llama2.c: comment out legacy "load from ggml model" logic

ochafik committed 3 years ago
llama2.c: convert special-cased "<0xXX>" single byte tokens from tokenizer.bin

ochafik committed 3 years ago