From 87f8b7dba1a334459b7401a6b88e68fd7e0ecc33 Mon Sep 17 00:00:00 2001
From: tackhwa <55059307+tackhwa@users.noreply.github.com>
Date: Sat, 26 Oct 2024 02:42:40 +0800
Subject: [PATCH] Update token length

---
 lightrag/llm.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lightrag/llm.py b/lightrag/llm.py
index 692937fb..ab459fc7 100644
--- a/lightrag/llm.py
+++ b/lightrag/llm.py
@@ -268,7 +268,7 @@ async def hf_model_if_cache(
     ).to("cuda")
     inputs = {k: v.to(hf_model.device) for k, v in input_ids.items()}
     output = hf_model.generate(
-        **input_ids, max_new_tokens=200, num_return_sequences=1, early_stopping=True
+        **input_ids, max_new_tokens=512, num_return_sequences=1, early_stopping=True
     )
     response_text = hf_tokenizer.decode(output[0][len(inputs["input_ids"][0]):], skip_special_tokens=True)
     if hashing_kv is not None: