Update README.md

README.md

@@ -5,10 +5,10 @@
 Notably, this CoT-enabled model was trained using only a single RTX 4090D, achieved through optimizations in both GPU VRAM and system RAM management, as well as specific techniques applied during the training steps.
 ### Model Overview
 
-**Hicoder-R1-Distill-Gemma-27B** is a large language model fine-tuned from Google's **Gemma-2 27B** (*Note: Assuming Gemma-2 27B as Gemma-3 is not publicly released*) base model. This model is specifically optimized for **Chain-of-Thought (CoT) reasoning** and **code generation** tasks. The "Distill" in the name suggests that knowledge distillation techniques may have been employed during the fine-tuning process, potentially leveraging outputs from a more powerful teacher model to enhance its reasoning and coding abilities.
+**Hicoder-R1-Distill-Gemma-27B** is a large language model fine-tuned from Google's **Gemma-3 27B**  base model. This model is specifically optimized for **Chain-of-Thought (CoT) reasoning** and **code generation** tasks.
 
-*   **Base Model:** google/gemma-2-27b (or specify the exact variant used, e.g., gemma-2-27b-it)
-*   **Fine-tuned by:** [Your Name/Organization]
+*   **Base Model:** google/gemma-3-27b 
+*   **Fine-tuned by:** tonyli8623
 *   **Focus Areas:** Chain-of-Thought (CoT), Code Generation, Code Explanation, Debugging
 *   **Language:** Primarily English for prompts and reasoning, generates code in multiple languages.
 
@@ -16,7 +16,7 @@ Notably, this CoT-enabled model was trained using only a single RTX 4090D, achie
 
 *   **Enhanced CoT Reasoning:** Explicitly trained to break down complex problems into intermediate steps before providing a final answer, particularly useful for complex coding or algorithmic tasks.
 *   **Strong Coding Capabilities:** Generates, explains, debugs, and translates code across various programming languages (e.g., Python, JavaScript, Java, C++, SQL, etc.).
-*   **Gemma-2 Foundation:** Built upon the powerful and efficient architecture of Google's Gemma-2 27B model.
+*   **Gemma-3 Foundation:** Built upon the powerful and efficient architecture of Google's Gemma-3 27B model.
 *   **Distillation Enhanced (Implied):** Potentially benefits from knowledge distillation for improved performance relative to standard fine-tuning on the target tasks.
 
 ### How to Use
@@ -28,7 +28,7 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 # Specify the path to your fine-tuned model (local or Hugging Face Hub ID)
-model_id = "[Your Hugging Face Model ID or Local Path, e.g., YourUsername/Hicoder-R1-Distill-Gemma-27B]"
+model_id = "tonyli8623/Hicoder-R1-Distill-Gemma-27B"
 
 # Load tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained(model_id)
@@ -90,7 +90,7 @@ print(response_cot)
 
 ### Limitations and Bias
 
-*   This model is based on Gemma-2, and inherits its capabilities and limitations.
+*   This model is based on Gemma-3, and inherits its capabilities and limitations.
 *   While fine-tuned for coding, it may still generate incorrect, inefficient, or insecure code. **Always review and test generated code thoroughly.**
 *   The model's knowledge is limited to its training data cutoff.
 *   Like all LLMs, it may exhibit biases present in the underlying training data.
@@ -98,7 +98,7 @@ print(response_cot)
 
 ### License
 
-The license for this model depends on the base Gemma-2 model's license and any additional terms you impose. The Gemma-2 models are typically governed by the "Gemma Terms of Use". Please consult the specific license file included with the model or the Gemma Terms of Use.
+The license for this model depends on the base Gemma-2 model's license and any additional terms you impose. The Gemma-3 models are typically governed by the "Gemma Terms of Use". Please consult the specific license file included with the model or the Gemma Terms of Use.
 
 *   **Gemma Terms of Use:** [Link to Google's Gemma Terms, e.g., https://ai.google.dev/gemma/terms]
 *   **Fine-tuning Specific License (if any):** [Specify if you add Apache 2.0, MIT, etc., or state it follows the base model license]
@@ -116,7 +116,7 @@ If you use this model in your research or work, please consider citing:
 }
 
 @misc{gemma2_2024,
-  title={Gemma 2 Technical Report},
+  title={Gemma 3 Technical Report},
   author={Gemma Team, Google},
   year={2024},
   howpublished={\url{https://ai.google.dev/gemma}} % Replace with actual Gemma 2 paper/report link if available
@@ -134,7 +134,7 @@ For questions, feedback, or issues, please contact tonyli288@gmail.com.
 
 ### 模型概述
 
-**Hicoder-R1-Distill-Gemma-27B** 是一个基于 Google **Gemma-2 27B** (*注意：假设基于 Gemma-2 27B，因为 Gemma-3 尚未公开发布*) 基础模型进行微调的大型语言模型。该模型专门针对**思维链 (Chain-of-Thought, CoT) 推理**和**代码生成**任务进行了优化。名称中的 "Distill" 暗示在微调过程中可能采用了知识蒸馏技术，或许利用了更强大的教师模型的输出来增强其推理和编码能力。
+**Hicoder-R1-Distill-Gemma-27B** 是一个基于 Google **Gemma-3 27B** (基���模型进行微调的大型语言模型。该模型专门针对**思维链 (Chain-of-Thought, CoT) 推理**和**代码生成**任务进行了优化。
 
 *   **基础模型:** google/gemma-2-27b (或指定使用的确切变体，例如 gemma-2-27b-it)
 *   **微调者:** [您的姓名/组织名称]
@@ -157,8 +157,7 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 # 指定您的微调模型的路径 (本地路径或 Hugging Face Hub ID)
-model_id = "[您的 Hugging Face 模型 ID 或本地路径, 例如: YourUsername/Hicoder-R1-Distill-Gemma-27B]"
-
+model_id = "tonyli8623/Hicoder-R1-Distill-Gemma-27B"
 # 加载分词器和模型
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
@@ -215,7 +214,7 @@ print(response_cot)
 
 ```
 
-**提示词技巧 (Prompting):** 为了获得最佳效果，尤其是在需要 CoT 推理时，请明确要求模型“逐步思考”或“在代码前提供你的推理过程”。除非您在微调过程中定义了自定义模板，否则请使用与基础 Gemma-2 模型关联的聊天模板。
+**提示词技巧 (Prompting):** 为了获得最佳效果，尤其是在需要 CoT 推理时，请明确要求模型“逐步思考”或“在代码前提供你的推理过程”。如添加system prompts "你是一位精通各种编程语言的代码工程师。在回答之前，请仔细思考问题，并创建一个逻辑连贯的思考过程，以<think>开始，以</think>结束，思考完后给出答案。"
 
 ### 局限性与偏见