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 /examples/server/bench/script.js | |
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 'examples/server/bench/script.js')
0 files changed, 0 insertions, 0 deletions