Change the vocab base to Xenova/gpt-4o

Author: nisparks

convert_hf_to_gguf.py

@@ -700,7 +700,7 @@ def get_vocab_base_pre(self, tokenizer) -> str:
             # ref: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
             res = "deepseek-r1-qwen"
         if chkhsh == "ccc2ef013c104be7bae2965776d611e1d7a8a2a9c547dd93a682c9a9fc80352e":
-            # ref: https://huggingface.co/microsoft/Phi-4-mini-instruct
+            # ref: https://huggingface.co/Xenova/gpt-4o
             res = "gpt-4o"
 
         if res is None:

convert_hf_to_gguf_update.py

@@ -109,7 +109,7 @@ class TOKENIZER_TYPE(IntEnum):
     {"name": "megrez",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Infinigence/Megrez-3B-Instruct"},
     {"name": "deepseek-v3",      "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/DeepSeek-V3"},
     {"name": "deepseek-r1-qwen", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"},
-    {"name": "gpt-4o",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/microsoft/Phi-4-mini-instruct", },
+    {"name": "gpt-4o",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Xenova/gpt-4o", },
 ]