From 7348bac6ab093855a6317aae542b766acf825731 Mon Sep 17 00:00:00 2001
From: ViperEkura <3081035982@qq.com>
Date: Fri, 19 Jun 2026 14:02:22 +0800
Subject: [PATCH] =?UTF-8?q?fix:=20=E8=A7=84=E8=8C=83=20generate.py=20?=
 =?UTF-8?q?=E5=91=BD=E4=BB=A4=E8=A1=8C=E6=8E=A5=E5=8F=A3?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- generate.py 清理描述文字，help 统一标注默认值
- max_tokens 默认改为 None，回退 model config max_len
- evaluate_ppl.py 同步清理描述文字
- params.md 同步 max_tokens 默认值
---
 assets/docs/params.md        |  2 +-
 scripts/eval/evaluate_ppl.py |  2 +-
 scripts/tools/generate.py    | 25 ++++++++++++++++---------
 3 files changed, 18 insertions(+), 11 deletions(-)

diff --git a/assets/docs/params.md b/assets/docs/params.md
index 4526b19..ee91ee5 100644
--- a/assets/docs/params.md
+++ b/assets/docs/params.md
@@ -161,7 +161,7 @@ See [Inference Guide](inference.md) for HTTP API documentation.
 | `--top_k` | int | `30` | Top-k filtering |
 | `--top_p` | float | `0.95` | Nucleus sampling threshold |
 | `--batch_size` | int | `1` | Batch size for generation |
-| `--max_tokens` | int | `2048` | Maximum tokens to generate |
+| `--max_tokens` | int | model config `max_len` | Maximum tokens to generate |
 
 Usage:
 ```bash
diff --git a/scripts/eval/evaluate_ppl.py b/scripts/eval/evaluate_ppl.py
index 970440f..94cc79b 100644
--- a/scripts/eval/evaluate_ppl.py
+++ b/scripts/eval/evaluate_ppl.py
@@ -86,7 +86,7 @@ def process_file(
 
 
 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Run perplexity with a Khaosz model.")
+    parser = argparse.ArgumentParser(description="Perplexity evaluation on JSONL text.")
     parser.add_argument(
         "--param_path", type=str, required=True, help="Path to the model directory."
     )
diff --git a/scripts/tools/generate.py b/scripts/tools/generate.py
index ccb7129..15af606 100644
--- a/scripts/tools/generate.py
+++ b/scripts/tools/generate.py
@@ -1,5 +1,6 @@
 import argparse
 import json
+from typing import Optional
 
 import torch
 
@@ -17,7 +18,7 @@ def processor(
     top_p: float,
     question_key: str,
     response_key: str,
-    max_tokens: int,
+    max_tokens: Optional[int],
     batch_size: int,
 ):
     # Load model and tokenizer
@@ -72,7 +73,7 @@ def processor(
 
 
 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Run generate with a Khaosz model.")
+    parser = argparse.ArgumentParser(description="Batch generation from JSONL file.")
 
     parser.add_argument(
         "--param_path", type=str, required=True, help="Path to the model directory."
@@ -93,36 +94,42 @@ if __name__ == "__main__":
         "--question_key",
         type=str,
         default="question",
-        help="Key for the question in the input JSON.",
+        help="Key for the question in the input JSON (default: question).",
     )
     parser.add_argument(
         "--response_key",
         type=str,
         default="response",
-        help="Key for the response in the output JSON.",
+        help="Key for the response in the output JSON (default: response).",
     )
     parser.add_argument(
         "--temperature",
         type=float,
         default=0.60,
-        help="Temperature for generating responses.",
+        help="Temperature for generating responses (default: 0.60).",
     )
     parser.add_argument(
-        "--top_k", type=int, default=30, help="Top-k value for generating responses."
+        "--top_k",
+        type=int,
+        default=30,
+        help="Top-k value for generating responses (default: 30).",
     )
     parser.add_argument(
         "--top_p",
         type=float,
         default=0.95,
-        help="Top-p value for generating responses.",
+        help="Top-p value for generating responses (default: 0.95).",
     )
     parser.add_argument(
-        "--batch_size", type=int, default=1, help="Batch size for generating responses."
+        "--batch_size",
+        type=int,
+        default=1,
+        help="Batch size for generating responses (default: 1).",
     )
     parser.add_argument(
         "--max_tokens",
         type=int,
-        default=2048,
+        default=None,
         help="Maximum tokens to generate (default: model config max_len).",
     )