llama.cpp/examples/tokenize
Jared Van Bortel 1b67731e18
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
2024-04-09 13:44:08 -04:00
..
CMakeLists.txt examples : add tokenize (#4039) 2023-11-17 17:36:44 +02:00
tokenize.cpp BERT tokenizer fixes (#6498) 2024-04-09 13:44:08 -04:00