Update README.md

README.md

@@ -4,13 +4,12 @@ language:
 - en
 - zh
 pipeline_tag: text-generation
-base_model: Qwen/Qwen3-4b
+base_model: Qwen/Qwen3-4B
 tags:
 - chat
 - function-calling
 - tool-use
 - star-method
-- sota
 library_name: transformers
 ---
 
@@ -18,23 +17,21 @@ library_name: transformers
 
 ## Introduction
 
-**STAR-4b** is a highly capable 4b 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.
+**STAR-4b** is a highly capable 4B parameter language model specialized in function calling.
 
-This model is the result of fine-tuning the `Qwen/Qwen3-4b` 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.
+This model is the result of fine-tuning the `Qwen/Qwen3-4B` 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.
 
 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.
 
-Our STAR-4b model significantly outperforms other open models under 1B parameters and even surpasses several larger models, demonstrating the effectiveness of the STAR methodology.
-
 ## Model Details
 
 - **Model Type**: Causal Language Model, fine-tuned for function calling.
-- **Base Model**: `Qwen/Qwen3-4b`
+- **Base Model**: `Qwen/Qwen3-4B`
 - **Training Framework**: STAR (CKD + Sim-RL)
 - **Architecture**: Transformer with RoPE, SwiGLU, RMSNorm, and Attention QKV bias.
-- **Number of Parameters**: ~4b
+- **Number of Parameters**: ~4B
 - **Context Length**: Supports up to 32,768 tokens.
 
 ## Requirements
@@ -100,7 +97,7 @@ For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTr
 
 ## Evaluation & Performance
 
-STAR-4b has achieved outstanding performance for models of its size on renowned function calling benchmarks.
+STAR-4b has achieved outstanding performance on renowned function calling benchmarks.
 
 - BFCLv3: Achieved 65.24% overall accuracy.
 - ACEBench: Achieved 74.10% summary score, demonstrating superior generalization and robustness.