rm inp/out files for models not having gguf

Author: ngxson

convert_hf_to_gguf.py

@@ -794,6 +794,9 @@ def get_vocab_base_pre(self, tokenizer) -> str:
         if chkhsh == "d353350c764d8c3b39c763113960e4fb4919bea5fbf208a0e3b22e8469dc7406":
             # ref: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct
             res = "llama4"
+        if chkhsh == "81d72c7348a9f0ebe86f23298d37debe0a5e71149e29bd283904c02262b27516":
+            # ref: https://huggingface.co/THUDM/glm-4-9b-chat
+            res = "chatglm-bpe"
         if chkhsh == "b6e8e1518dc4305be2fe39c313ed643381c4da5db34a98f6a04c093f8afbe99b":
             # ref: https://huggingface.co/THUDM/glm-4-9b-hf
             res = "glm4"

convert_hf_to_gguf_update.py

@@ -417,6 +417,10 @@ def get_vocab_base_pre(self, tokenizer) -> str:
         logger.error(f"Failed to load tokenizer for model {name}. Error: {e}")
         continue  # Skip this model and continue with the next one in the loop
 
+    if not os.path.exists(f"models/ggml-vocab-{name}.gguf"):
+        logger.info(f"Skip vocab files for model {name}, no GGUF file found")
+        continue
+
     with open(f"models/ggml-vocab-{name}.gguf.inp", "w", encoding="utf-8") as f:
         for text in tests:
             f.write(f"{text}")