diff options
| author | Jared Van Bortel <jared@nomic.ai> | 2024-04-09 13:44:08 -0400 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-04-09 13:44:08 -0400 |
| commit | 1b67731e184e27a465b8c5476061294a4af668ea (patch) | |
| tree | 15a2d877029fb509a34e462c227475bc7d6dc31e /convert-persimmon-to-gguf.py | |
| parent | c4a3a4ff47d62d2503ddf9bd91b58c21f04fe3c3 (diff) | |
BERT tokenizer fixes (#6498)
Key changes:
* BERT conversion: fix abuse of LlamaHfVocab, do not set BOS or EOS
* Nomic Embed conversion: pad vocab instead of slicing embedding tensor
* llama_tokenize: handle added special tokens like HF does
Diffstat (limited to 'convert-persimmon-to-gguf.py')
| -rwxr-xr-x | convert-persimmon-to-gguf.py | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/convert-persimmon-to-gguf.py b/convert-persimmon-to-gguf.py index ccb99279..69be17f9 100755 --- a/convert-persimmon-to-gguf.py +++ b/convert-persimmon-to-gguf.py @@ -1,4 +1,6 @@ #!/usr/bin/env python3 +from __future__ import annotations + import argparse import os import sys |