Update README.md (#1)

- Update README.md (94685ece307d0ef0c78b7f0b545b2422944b05f7)


Co-authored-by: Xuchen Pan <panxuchen@users.noreply.huggingface.co>

README.md

@@ -6,19 +6,19 @@ language:
 base_model:
 - Qwen/Qwen3.5-2B
 ---
-# CoPaw-Flash-2B
-**CoPaw-Flash** is a lightweight model deeply optimized for the CoPaw autonomous agent scenario. Since its training phase, the model has been specifically refined for CoPaw tasks, delivering enhanced agentic performance in tool invocation, command execution, memory management, and multi-step planning.
+# QwenPaw-Flash-2B
+**QwenPaw-Flash** is a lightweight model deeply optimized for the QwenPaw autonomous agent scenario. Since its training phase, the model has been specifically refined for QwenPaw tasks, delivering enhanced agentic performance in tool invocation, command execution, memory management, and multi-step planning.
 
 ## Capability
-The core strength of CoPaw-Flash stems from its native integration with the CoPaw ecosystem. We have constructed extensive, high-quality agent trajectory data sampled from real CoPaw environments, systematically enhancing the model's proficiency in high-frequency daily scenarios. Key features include:
+The core strength of QwenPaw-Flash stems from its native integration with the QwenPaw ecosystem. We have constructed extensive, high-quality agent trajectory data sampled from real QwenPaw environments, systematically enhancing the model's proficiency in high-frequency daily scenarios. Key features include:
 
 + **Active Memory Management:** Autonomously identifies, stores, and retrieves persistent user preferences and task states, ensuring high logical consistency across multi-turn interactions.
 + **Native File Parsing:** Optimized for terminal operations and file system orchestration. Excels at generating precise CLI commands and executing complex, multi-step file I/O tasks.
 + **Efficient Information Search:** Enhanced for web-search tool invocation. Features precise search intent recognition and multi-step web navigation to effectively identify and query online information.
-+ **Intelligent Guidance:** Built-in awareness of the CoPaw feature map. Proactively suggests functional paths and troubleshooting based on real-time operational context.
++ **Intelligent Guidance:** Built-in awareness of the QwenPaw feature map. Proactively suggests functional paths and troubleshooting based on real-time operational context.
 
 ## Model Overview
-CoPaw-Flash-2B/4B/9B is fine-tuned from Qwen3.5-2B/4B/9B, sharing the same architectural parameters.
+QwenPaw-Flash-2B/4B/9B is fine-tuned from Qwen3.5-2B/4B/9B, sharing the same architectural parameters.
 
 + **Type:** Causal Language Model with Vision Encoder
 + **Training Stage:** Post-training
@@ -39,24 +39,24 @@ CoPaw-Flash-2B/4B/9B is fine-tuned from Qwen3.5-2B/4B/9B, sharing the same archi
 + **Context Length:** 262,144 tokens natively
 
 ## Benchmark Results
-The complexity of CoPaw's context engineering and tool usage poses heightened challenges for model evaluation. To address this, we have developed a dedicated benchmark tailored to the CoPaw environment. This benchmark systematically evaluates model performance across five high-frequency usage scenarios, covering key operational dimensions.
+The complexity of QwenPaw's context engineering and tool usage poses heightened challenges for model evaluation. To address this, we have developed a dedicated benchmark tailored to the QwenPaw environment. This benchmark systematically evaluates model performance across five high-frequency usage scenarios, covering key operational dimensions.
 
-Results indicate that CoPaw-Flash delivers substantial improvements across multiple task categories, achieving performance comparable to leading flagship models—all while maintaining significantly lower resource requirements.
+Results indicate that QwenPaw-Flash delivers substantial improvements across multiple task categories, achieving performance comparable to leading flagship models—all while maintaining significantly lower resource requirements.
 
 <img src="https://img.alicdn.com/imgextra/i2/O1CN01uQsLX61XbwkjLtHuP_!!6000000002943-2-tps-1264-888.png" width="632" title="" crop="0,0,1,1" id="ufe625d3c" class="ne-image">
 
-Figure 1: CoPaw-Flash-9B compared with other models.
+Figure 1: QwenPaw-Flash-9B compared with other models.
 
 <img src="https://img.alicdn.com/imgextra/i1/O1CN01OKDCHQ1yuic00Qmyu_!!6000000006639-2-tps-1984-975.png" width="628" title="" crop="0,0,1,1" id="u15257ae6" class="ne-image">
 
-Figure 2: CoPaw-Flash-2B/4B/9B compared with their respective baseline models.
+Figure 2: QwenPaw-Flash-2B/4B/9B compared with their respective baseline models.
 
 ## Quickstart
-### <font style="color:rgb(31, 35, 40);">Serving CoPaw-Flash</font>
-CoPaw-Flash<font style="color:rgb(31, 35, 40);"> can be served via APIs using popular inference frameworks. Below are example commands to launch OpenAI-compatible API servers for CoPaw-Flash.</font>
+### <font style="color:rgb(31, 35, 40);">Serving QwenPaw-Flash</font>
+QwenPaw-Flash<font style="color:rgb(31, 35, 40);"> can be served via APIs using popular inference frameworks. Below are example commands to launch OpenAI-compatible API servers for QwenPaw-Flash.</font>
 
 #### <font style="color:rgb(31, 35, 40);">vLLM</font>
-vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Since CoPaw-Flash leverages the Qwen3.5 architecture, the latest vLLM version is required for optimal compatibility. You can install it in a fresh environment using:
+vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Since QwenPaw-Flash leverages the Qwen3.5 architecture, the latest vLLM version is required for optimal compatibility. You can install it in a fresh environment using:
 
 ```plain
 uv pip install vllm --torch-backend=auto --extra-index-url https://wheels.vllm.ai/nightly
@@ -82,8 +82,8 @@ vllm serve <your_model_path> \
 
 
 
-### Using CoPaw-Flash via Chat Completions API
-Once the server is running, you can access CoPaw-Flash via standard HTTP requests or OpenAI-compatible SDKs.
+### Using QwenPaw-Flash via Chat Completions API
+Once the server is running, you can access QwenPaw-Flash via standard HTTP requests or OpenAI-compatible SDKs.
 
 #### <font style="color:rgb(31, 35, 40);">Prerequisites</font>
 Ensure the OpenAI Python SDK is installed and your environment variables are configured:
@@ -107,7 +107,7 @@ from openai import OpenAI
 client = OpenAI()
 
 messages = [
-    {"role": "user", "content": "Hello, Copaw!"},
+    {"role": "user", "content": "Hello, QwenPaw!"},
 ]
 
 chat_response = client.chat.completions.create(
@@ -125,7 +125,7 @@ print("Chat response:", chat_response)
 ```
 
 ## Contact Us
-CoPaw-Flash is developed by the AgentScope Team. If you would like to leave us a message, feel free to get in touch through the channels below.
+QwenPaw-Flash is developed by the AgentScope Team. If you would like to leave us a message, feel free to get in touch through the channels below.
 
 
 | [Discord](https://discord.gg/eYMpfnkG8h)                     | [X (Twitter)](https://x.com/agentscope_ai)                   | [DingTalk](https://qr.dingtalk.com/action/joingroup?code=v1,k1,OmDlBXpjW+I2vWjKDsjvI9dhcXjGZi3bQiojOq3dlDw=&_dt_no_comment=1&origin=11) |