From c04ddb699055994a0f0b8f22ee3010f4cdc183b8 Mon Sep 17 00:00:00 2001 From: Galunid Date: Mon, 23 Oct 2023 16:57:50 +0200 Subject: [PATCH] Add mpt --- convert-mpt-hf-to-gguf.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/convert-mpt-hf-to-gguf.py b/convert-mpt-hf-to-gguf.py index 2d2fa2329..70d154b3f 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)