From: Sigbjørn Skjæret <redacted>
Date: Sat, 18 Apr 2026 07:36:41 +0000 (+0200)
Subject: convert : fix (ignore for now) typings errors (#22002)
X-Git-Tag: upstream/0.0.10438~1603
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=89a5474f0e7d96450adf1764a2c79f4e2d55fa8b;p=pkg%2Fggml%2Fsources%2Fllama.cpp

convert : fix (ignore for now) typings errors (#22002)
---

diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index 42d559dfe..2df5e94fe 100755
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -10912,14 +10912,14 @@ class NemotronHModel(GraniteHybridModel):
         vocab_size = -(vocab_size // -pad_vocab) * pad_vocab
         self.hparams["vocab_size"] = vocab_size
 
-        assert max(tokenizer.vocab.values()) < vocab_size
+        assert max(tokenizer.vocab.values()) < vocab_size  # ty: ignore[unresolved-attribute]
 
         tokpre = self.get_vocab_base_pre(tokenizer)
 
-        reverse_vocab = {id_: encoded_tok for encoded_tok, id_ in tokenizer.vocab.items()}
-        added_vocab = tokenizer.get_added_vocab()
+        reverse_vocab = {id_: encoded_tok for encoded_tok, id_ in tokenizer.vocab.items()}  # ty: ignore[unresolved-attribute]
+        added_vocab = tokenizer.get_added_vocab()  # ty: ignore[unresolved-attribute]
 
-        added_tokens_decoder = tokenizer.added_tokens_decoder
+        added_tokens_decoder = tokenizer.added_tokens_decoder  # ty: ignore[unresolved-attribute]
 
         for i in range(vocab_size):
             if i not in reverse_vocab:
@@ -10930,7 +10930,7 @@ class NemotronHModel(GraniteHybridModel):
                 if token in added_vocab:
                     if not added_tokens_decoder[i].normalized:
                         previous_token = token
-                        token = tokenizer.decode(tokenizer.encode(token, add_special_tokens=False))
+                        token = tokenizer.decode(tokenizer.encode(token, add_special_tokens=False))  # ty: ignore[unresolved-attribute, invalid-assignment]
                         if previous_token != token:
                             logger.info(f"{repr(previous_token)} is encoded and decoded back to {repr(token)} using AutoTokenizer")