Update README.md

README.md

@@ -1,72 +1,106 @@
 ---
-# 基础信息
-license: apache-2.0  # 或者你选择的开源许可证
+license: apache-2.0
 language:
-- zh # 中文
+- en
+- zh
+pipeline_tag: text-generation
+base_model: Qwen/Qwen3-1.7B
+tags:
+- chat
+- function-calling
+- tool-use
+- star-method
+- sota
 library_name: transformers
-base_model: Qwen/Qwen2-0.5B # 填写你使用的原始基础模型 ID
-
-# 评测结果 - 这是展示 SOTA 的核心部分！
-results:
-- task:
-    type: text-generation
-    name: "中文大模型安全评测 (BFCL)"
-  dataset:
-    type: EvalPlus/bfcl # 假设这是BFCL在HF上的数据集ID，如果不是，请写真实名称
-    name: BFCL
-    split: test
-  metrics:
-  - type: bfcl_score  # 自定义一个指标类型
-    value: 95.8       # 你的SOTA分数！
-    name: "BFCL Score"
-    verified: false # 如果结果被官方验证，可以改为 true
 ---
 
+# STAR-1b7
 
-# Qwen3-0.6B-BFCL-SOTA：在 BFCL 安全评测上达到新 SOTA 的模型
+## Introduction
 
-这是一个在 `qwen3-0.6b` 基础上微调的模型，专注于提升在中文安全场景下的表现。
-我们在 [BFCL (中文大模型安全评测基准)](https://github.com/EvalPlus/bfcl) 上取得了最先进的（SOTA）结果。
+**STAR-1b7** is a highly capable 1.7B parameter language model specialized in function calling, achieving excellent performances on the [Berkeley Function Calling Leaderboard (BFCL)](https://huggingface.co/spaces/gorilla-llm/berkeley-function-calling-leaderboard) for models in its size class.
 
-## 模型描述
+This model is the result of fine-tuning the `Qwen/Qwen3-1.7B` base model using the novel **STAR (Similarity-guided Teacher-Assisted Refinement)** framework. STAR is a holistic training curriculum designed to effectively transfer the advanced capabilities of large language models (LLMs) into "super-tiny" models, making them powerful, accessible, and efficient for real-world agentic applications.
 
-*   **基础模型**: [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) (请替换为实际基础模型)
-*   **微调数据**: 描述你用于微调的数据集，例如数据来源、规模、处理方法等。
-*   **训练过程**:
-    *   **硬件**: 2 * A100 (80GB)
-    *   **框架**: transformers, peft (LoRA)
-    *   **超参数**: learning_rate=2e-5, epochs=3, batch_size=32 ...
+The key innovations of the STAR framework include:
+- **Similarity-guided RL (Sim-RL)**: A reinforcement learning mechanism that uses a fine-grained, similarity-based reward signal. This provides a more robust and continuous signal for policy optimization compared to simple binary rewards, which is crucial for complex, multi-solution tasks like function calling.
+- **Constrained Knowledge Distillation (CKD)**: An advanced training objective that augments top-k forward KL divergence to suppress confidently incorrect predictions. This ensures training stability while preserving the model's exploration capacity, creating a strong foundation for the subsequent RL phase.
 
-## 评测结果
+Our STAR-1b7 model significantly outperforms other open models under 1B parameters and even surpasses several larger models, demonstrating the effectiveness of the STAR methodology.
 
-我们在 BFCL 测试集上进行了评估，取得了以下成绩，超过了之前的 SOTA 模型 [之前的SOTA模型名称]。
+## Model Details
 
-| Metric       | Score |
-|--------------|-------|
-| **BFCL Score** | **95.8**  |
-| Sub-Metric 1 | 94.2  |
-| Sub-Metric 2 | 97.5  |
+- **Model Type**: Causal Language Model, fine-tuned for function calling.
+- **Base Model**: `Qwen/Qwen3-1.7B`
+- **Training Framework**: STAR (CKD + Sim-RL)
+- **Architecture**: Transformer with RoPE, SwiGLU, RMSNorm, and Attention QKV bias.
+- **Number of Parameters**: ~1.7B
+- **Context Length**: Supports up to 32,768 tokens.
 
-为了保证结果的可复现性，我们使用了 [此处的评估脚本](链接到你的评估代码)。
+## Requirements
 
-## 如何使用
+The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`.
+With `transformers<4.51.0`, you will encounter the following error:
+```
+KeyError: 'qwen3'
+```
 
-下面是如何使用 `transformers` 库加载和运行此模型的示例：
+## Quickstart
+
+Here is a code snippet showing how to load STAR-1b7 and use it for a chat-based task.
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_id = "你的HF用户名/你的模型名" # 例如：my-username/qwen3-0.6b-bfcl-sota
-
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
-
-prompt = "在这里输入你的测试提示..."
-inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-outputs = model.generate(**inputs, max_new_tokens=100)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-
-免责声明和许可证
-本模型遵循 Apache 2.0 许可证。使用时请遵守相关法律法规，并注意模型可能产生不可预见的输出。
-
-```
+model_name = "star-lab/STAR-1b7"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Example prompt that could trigger a function call
+prompt = "What is the current weather in San Francisco?"
+messages = [
+    {"role": "system", "content": "You are a helpful assistant with access to external tools."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=32768
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(response)
+```
+
+For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint:
+- SGLang:
+    ```shell
+    python -m sglang.launch_server --model-path star-lab/STAR-1b7 --reasoning-parser qwen3
+    ```
+- vLLM:
+    ```shell
+    vllm serve star-lab/STAR-1b7 --enable-reasoning --reasoning-parser deepseek_r1
+    ```
+
+For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported STAR-1b7.
+
+## Evaluation & Performance
+
+STAR-1b7 has achieved outstanding performance for models of its size on renowned function calling benchmarks.
+
+- BFCLv3: Achieved 56.05% overall accuracy.
+- ACEBench: Achieved 60.90% summary score, demonstrating superior generalization and robustness.