llama : tokenizer fixes (#2549)

Browse source

* Merge tokenizer fixes into the gguf branch.

* Add test vocabularies

...

This commit is contained in:

goerch 2023-08-14 18:30:28 +02:00 • committed by GitHub

parent 8af3a99ff1

commit ec1b100720

No known key found for this signature in database

GPG key ID: 4AEE18F83AFDEB23

17 changed files with 612 additions and 147 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

BIN

models/ggml-vocab-aquila.bin Normal file

View file

Binary file not shown.

BIN

models/ggml-vocab-llama.bin Normal file

View file

Binary file not shown.

BIN

models/ggml-vocab.bin

View file

Binary file not shown.