convert : add "tokenizer.ggml.pre" GGUF KV (wip)

This commit is contained in:
Georgi Gerganov 2024-04-26 19:21:55 +03:00
parent e3f6dc7409
commit 9b4d63ae53
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
6 changed files with 58 additions and 7 deletions

View file

@ -99,6 +99,7 @@ def main():
tokens, scores, toktypes = _get_sentencepiece_tokenizer_info(args.model_dir)
gguf_writer.add_tokenizer_model('llama')
gguf_writer.add_tokenizer_pre('default')
gguf_writer.add_token_list(tokens)
gguf_writer.add_token_scores(scores)
gguf_writer.add_token_types(toktypes)