diff options
Diffstat (limited to 'convert-refact-hf-to-gguf.py')
| -rwxr-xr-x | convert-refact-hf-to-gguf.py | 17 |
1 files changed, 13 insertions, 4 deletions
diff --git a/convert-refact-hf-to-gguf.py b/convert-refact-hf-to-gguf.py index 934f3852..f0cfe84d 100755 --- a/convert-refact-hf-to-gguf.py +++ b/convert-refact-hf-to-gguf.py @@ -139,15 +139,24 @@ tokenizer = AutoTokenizer.from_pretrained(dir_model) vocab_size = hparams.get("vocab_size", len(tokenizer.vocab)) assert max(tokenizer.vocab.values()) < vocab_size +added_vocab = tokenizer.get_added_vocab() reverse_vocab = {id: encoded_tok for encoded_tok, id in tokenizer.vocab.items()} for i in range(vocab_size): - tokens.append(reverse_vocab[i] if i in reverse_vocab else f"[PAD{i}]") - scores.append(0.0) # dummy - toktypes.append(gguf.TokenType.NORMAL) + if i not in reverse_vocab: + tokens.append(f"[PAD{i}]") + toktypes.append(gguf.TokenType.USER_DEFINED) + elif reverse_vocab[i] in added_vocab: + tokens.append(reverse_vocab[i]) + 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) gguf_writer.add_token_list(tokens) -gguf_writer.add_token_scores(scores) gguf_writer.add_token_types(toktypes) special_vocab = gguf.SpecialVocab(dir_model, load_merges=True, n_vocab = len(tokens)) |