最新哦，分词策略放到cli了

llm_server/rag_server.py

@@ -71,7 +71,7 @@ def load_models():
     global token_true_id, token_false_id, prefix_tokens, suffix_tokens, max_rerank_length
     token_false_id = rerank_tokenizer.convert_tokens_to_ids("no")
     token_true_id  = rerank_tokenizer.convert_tokens_to_ids("yes")
-    max_rerank_length = 8192
+    max_rerank_length = 32768
 
     prefix = "<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be \"yes\" or \"no\".<|im_end|>\n<|im_start|>user\n"
     suffix = "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n"
@@ -111,7 +111,6 @@ async def get_embeddings(req: EmbedRequest):
         input_texts,
         padding=True,
         truncation=True,
-        max_length=8192,
         return_tensors="pt",
     ).to(embed_model.device)