llama.cpp
Update llama2.c converter to read vocab and write models in GGUF format
#2751
Merged
Merged
Update llama2.c converter to read vocab and write models in GGUF format #2751
ggerganov
merged
8 commits into
ggml-org:master
from
ochafik:llama2c-gguf
llama2.c: direct gguf output (WIP)
5132130a
Simplify vector building logic
463e1178
llama2.c gguf conversion: fix token types in converter
63174b80
llama2.c: support copying vocab from a llama gguf model file
c88362d1
llama2.c: update default path for vocab model + readme
df3b81ab
llama2.c: use defines for gguf keys
20c44711
llama2.c: escape whitespaces w/ U+2581 in vocab converter the llama.c…
0722e58a
llama2.c converter: cleanups + take n_ff from config
c58792c7
ochafik
changed the title 
ggerganov
approved these changes
on 2023-08-27
Login to write a write a comment.
Login via GitHub