From a005c49d476ed5a283c9ec0d2a6b524723f4d925 Mon Sep 17 00:00:00 2001
From: VoyagerX <voyagerx@163.com>
Date: Thu, 23 Apr 2026 15:47:15 +0000
Subject: [PATCH] Upload README.md to ModelScope hub

---
 README.md | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/README.md b/README.md
index 1bb065f..bfe0ecb 100644
--- a/README.md
+++ b/README.md
@@ -667,8 +667,7 @@ export OPENAI_API_KEY="EMPTY"
 > We recommend using the following set of sampling parameters for generation
 > - Thinking mode for general tasks: `temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0`
 > - Thinking mode for precise coding tasks (e.g. WebDev): `temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0`
-> - Instruct (or non-thinking) mode for general tasks: `temperature=0.7, top_p=0.8, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0`
-> - Instruct (or non-thinking) mode for reasoning tasks: `temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0`
+> - Instruct (or non-thinking) mode: `temperature=0.7, top_p=0.80, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0`
 >
 > Please note that the support for sampling parameters varies according to inference frameworks.
 
@@ -728,7 +727,7 @@ messages = [
     }
 ]
 
-response = client.chat.completions.create(
+chat_response = client.chat.completions.create(
     model="Qwen/Qwen3.6-35B-A3B",
     messages=messages,
     max_tokens=81920,
@@ -773,7 +772,7 @@ messages = [
 #
 # By default, `fps=2` and `do_sample_frames=True`.
 # With `do_sample_frames=True`, you can customize the `fps` value to set your desired video sampling rate.
-response = client.chat.completions.create(
+chat_response = client.chat.completions.create(
     model="Qwen/Qwen3.6-35B-A3B",
     messages=messages,
     max_tokens=81920,
@@ -1011,10 +1010,8 @@ To achieve optimal performance, we recommend the following settings:
        `temperature=1.0`, `top_p=0.95`, `top_k=20`, `min_p=0.0`, `presence_penalty=1.5`, `repetition_penalty=1.0`  
      - **Thinking mode for precise coding tasks (e.g., WebDev)**:  
        `temperature=0.6`, `top_p=0.95`, `top_k=20`, `min_p=0.0`, `presence_penalty=0.0`, `repetition_penalty=1.0`  
-     - **Instruct (or non-thinking) mode for general tasks**:  
-       `temperature=0.7`, `top_p=0.8`, `top_k=20`, `min_p=0.0`, `presence_penalty=1.5`, `repetition_penalty=1.0`  
-     - **Instruct (or non-thinking) mode for reasoning tasks**:  
-       `temperature=1.0`, `top_p=1.0`, `top_k=40`, `min_p=0.0`, `presence_penalty=2.0`, `repetition_penalty=1.0`  
+     - **Instruct (or non-thinking) mode**:  
+       `temperature=0.7`, `top_p=0.80`, `top_k=20`, `min_p=0.0`, `presence_penalty=1.5`, `repetition_penalty=1.0` 
    - For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
 
 2. **Adequate Output Length**: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 81,920 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance.