Update README.md

README.md

@@ -26,17 +26,17 @@ We have conducted a comprehensive evaluation of Ling-2.6-flash across multiple a
 
 Beyond agent tasks, Ling-2.6-flash also delivers strong performance across **general knowledge**,**mathematical reasoning**, **instruction following**, and **long-context understanding**, remains well aligned with SOTA models in the same size class.
 <div align="center">
-<img src="https://mdn.alipayobjects.com/huamei_3p6pd0/afts/img/FOkPQZDdKtkAAAAAgCAAAAgADryCAQFr/original" width="8001" title="" crop="0,0,1,1" id="u4a7a4034" class="ne-image">
+<img src="https://mdn.alipayobjects.com/huamei_3p6pd0/afts/img/KhFxSrxyF5IAAAAAgCAAAAgADryCAQFr/original" width="8001" title="" crop="0,0,1,1" id="u4a7a4034" class="ne-image">
 </div>
 
 <div align="center">
-<img src="https://mdn.alipayobjects.com/huamei_3p6pd0/afts/img/_rp_TKkkG4wAAAAAgBAAAAgADryCAQFr/original" width="8001" title="" crop="0,0,1,1" id="uc95688f2" class="ne-image">
+<img src="https://mdn.alipayobjects.com/huamei_3p6pd0/afts/img/4bI1SK8pNM8AAAAAgBAAAAgADryCAQFr/original" width="8001" title="" crop="0,0,1,1" id="uc95688f2" class="ne-image">
 </div>
 
 > + **<font style="color:rgb(38, 38, 38);">PinchBench</font>**<font style="color:rgb(38, 38, 38);">: Comparative scores are retrieved directly from the official PinchBench leaderboard (as of April 20, 2026), adhering to their evaluation modes (potentially Reasoning Mode). </font>
 > + **<font style="color:rgb(38, 38, 38);">Claw-Eval</font>**<font style="color:rgb(38, 38, 38);">: Comparative scores are sourced from the official Claw-Eval leaderboard (version dated 2026-03-25), adhering to their evaluation modes (potentially Reasoning Mode). Official scores for GPT-OSS-120B and GPT-5.4-mini are currently unavailable and have been omitted.</font>
 > + **<font style="color:rgb(38, 38, 38);">TAU2-Bench</font>**<font style="color:rgb(38, 38, 38);">: Evaluations are conducted using official v1.0.0 code and datasets. Following the GLM-5 evaluation protocol, we applied minor prompt adjustments in the Retail and Telecom domains to ensure users express requests clearly and to prevent premature session termination. Additionally, GPT-5.2 was utilized as the User Agent across all evaluated domains.</font>
-> + **<font style="color:rgb(38, 38, 38);">IFBench</font>**<font style="color:rgb(38, 38, 38);">: Scores for GPT-OSS-120B (low) and GPT-5.4-mini (Non-Reasoning) are sourced from the AA (Artificial Analysis) Leaderboard. All other model performance data are based on internal evaluation results.</font>
+> + **<font style="color:rgb(38, 38, 38);">IFBench</font>**<font style="color:rgb(38, 38, 38);">: Scores for GPT-OSS-120B (low) and GPT-5.4-mini (Non-Reasoning) are sourced from the AA(Artificial Analysis) Leaderboard. All other model performance data are based on internal evaluation results.</font>
 >
 
 ### Architecture
@@ -79,9 +79,6 @@ Both BF16 and FP8 models are supported by SGLang now. It depends on the dtype of
 **Server**
 
 **1. Standard Inference (Without MTP)**
-
-For standard, auto-regressive generation, you can load and run the model using the default `transformers` pipeline.
-
 ```bash
 python -m sglang.launch_server \
     --model-path $MODEL_PATH \
@@ -95,10 +92,8 @@ python -m sglang.launch_server \
 ```
 
 **2. Inference with MTP (Multi-Token Prediction)**  
-To significantly accelerate text generation, this model supports Multi-Token Prediction (MTP). You can enable it by passing the relevant flags during model initialization or generation.
 
 ```bash
-# mtp
 python -m sglang.launch_server \
     --model-path $MODEL_PATH \
     --tp-size 4 \