diff options
Diffstat (limited to 'convert-mpt-hf-to-gguf.py')
-rwxr-xr-x | convert-mpt-hf-to-gguf.py | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/convert-mpt-hf-to-gguf.py b/convert-mpt-hf-to-gguf.py index 2d2fa232..70d154b3 100755 --- a/convert-mpt-hf-to-gguf.py +++ b/convert-mpt-hf-to-gguf.py @@ -136,9 +136,11 @@ for i in range(vocab_size): tokens.append(f"[PAD{i}]") toktypes.append(gguf.TokenType.USER_DEFINED) elif reverse_vocab[i] in added_vocab: - # NOTE: wouldn't we like to distinguish CONTROL tokens here? tokens.append(reverse_vocab[i]) - toktypes.append(gguf.TokenType.USER_DEFINED) + if tokenizer.added_tokens_decoder[i].special: + toktypes.append(gguf.TokenType.CONTROL) + else: + toktypes.append(gguf.TokenType.USER_DEFINED) else: tokens.append(reverse_vocab[i]) toktypes.append(gguf.TokenType.NORMAL) |