convert : add t5 tokenizer tests

convert-hf-to-gguf-update.py

@@ -45,6 +45,7 @@ class TOKENIZER_TYPE(IntEnum):
     SPM = auto()
     BPE = auto()
     WPM = auto()
+    UGM = auto()
 
 
 # TODO: this string has to exercise as much pre-tokenizer functionality as possible
@@ -85,6 +86,7 @@ models = [
     {"name": "smaug-bpe",      "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/abacusai/Smaug-Llama-3-70B-Instruct", },
     {"name": "poro-chat",      "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LumiOpen/Poro-34B-chat", },
     {"name": "jina-v2-code",   "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-code", },
+    {"name": "t5",             "tokt": TOKENIZER_TYPE.UGM, "repo": "https://huggingface.co/google-t5/t5-small", },
 ]
 
 
@@ -106,9 +108,13 @@ def download_model(model):
     os.makedirs(f"models/tokenizers/{name}", exist_ok=True)
 
     files = ["config.json", "tokenizer.json", "tokenizer_config.json"]
+
     if tokt == TOKENIZER_TYPE.SPM:
         files.append("tokenizer.model")
 
+    if tokt == TOKENIZER_TYPE.UGM:
+        files.append("spiece.model")
+
     for file in files:
         save_path = f"models/tokenizers/{name}/{file}"
         if os.path.isfile(save_path):
@@ -131,7 +137,7 @@ for model in models:
     name = model["name"]
     tokt = model["tokt"]
 
-    if tokt == TOKENIZER_TYPE.SPM:
+    if tokt == TOKENIZER_TYPE.SPM or tokt == TOKENIZER_TYPE.UGM:
         continue
 
     # Skip if the tokenizer folder does not exist or there are other download issues previously
@@ -262,6 +268,7 @@ tests = [
     "\n =",
     "' era",
     "Hello, y'all! How are you 😁 ?我想在apple工作1314151天～",
+    "!!!!!!",
     "3",
     "33",
     "333",