Update special token handling in conversion scripts for gpt2 derived tokenizers (#3746)

We still have the heads up in `README.md` regarding `bpe` tokenizers and this patch is needed for 

- a couple of tokenizer tests
- some more `special` and `non-special` added tokens handling (as far as I understand it)

* Update special token handling

* Add mpt

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)