add embedding model tokenizer chkhsh

Author: ngxson

convert_hf_to_gguf.py

@@ -809,6 +809,9 @@ def get_vocab_base_pre(self, tokenizer) -> str:
         if chkhsh == "1431a23e583c97432bc230bff598d103ddb5a1f89960c8f1d1051aaa944d0b35":
             # ref: https://huggingface.co/sapienzanlp/Minerva-7B-base-v1.0
             res = "minerva-7b"
+        if chkhsh == "d4540891389ea895b53b399da6ac824becc30f2fba0e9ddbb98f92e55ca0e97c":
+            # ref: https://huggingface.co/Qwen/Qwen3-Embedding-0.6B
+            res = "qwen2"
 
         if res is None:
             logger.warning("\n")
@@ -3107,6 +3110,9 @@ def _get_cls_out_tensor(self, data_torch: Tensor) -> Tensor:
     def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
         is_rerank = self.token_false_id is not None and self.token_true_id is not None
 
+        if not name.startswith("model."):
+            name = "model." + name
+
         if is_rerank:
             if self.is_tied_embeddings and "embed_tokens" in name:
                 return [

convert_hf_to_gguf_update.py

@@ -137,6 +137,7 @@ class TOKENIZER_TYPE(IntEnum):
     {"name": "chatglm-bpe", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/THUDM/glm-4-9b-chat", "chkhsh": "81d72c7348a9f0ebe86f23298d37debe0a5e71149e29bd283904c02262b27516"},
     {"name": "glm4", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/THUDM/glm-4-9b-hf", "chkhsh": "a1336059768a55c99a734006ffb02203cd450fed003e9a71886c88acf24fdbc2"},
     {"name": "minerva-7b", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/sapienzanlp/Minerva-7B-base-v1.0", "chkhsh": "1431a23e583c97432bc230bff598d103ddb5a1f89960c8f1d1051aaa944d0b35"},
+    {"name": "qwen2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "chkhsh": "d4540891389ea895b53b399da6ac824becc30f2fba0e9ddbb98f92e55ca0e97c"},
 ]