Update README.md

README.md

@@ -1,3 +1,74 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+tags:
+- GPTQ
+license: apache-2.0
+datasets:
+- kxdw2580/catgirl-dataset
+language:
+- zh
+base_model:
+- kxdw2580/DeepSeek-R1-0528-Qwen3-8B-catgirl-v2.5
+---
+
+This model is the **GPTQ-v2 8-bit quantized version** of [`kxdw2580/DeepSeek-R1-0528-Qwen3-8B-catgirl-v2.5`](https://huggingface.co/kxdw2580/DeepSeek-R1-0528-Qwen3-8B-catgirl-v2.5). The quantization process resulted in minimal loss, with an average of **0.64539...**, which has been validated through internal few-shot benchmark tests.
+
+Below is the original model's README:
+
+---
+# kxdw2580/DeepSeek-R1-0528-Qwen3-8B-catgirl-v2.5  
+
+This new model series integrates updated datasets, base architectures, and fine-tuning methodologies. Based on **Qwen3**, it includes models with parameter counts of **8B** and **1.7B**.  
+
+Key updates focus on **daily conversations**, **creative generation**, **basic mathematics**, and **code generation**. Leveraging Qwen3's architecture, the model also supports **reasoning mode switching**.  
+
+🔍 **Fine-tuning records** are available on **SwanLab**:  
+1. [First Fine-tuning](https://swanlab.cn/@shadow01a/qwen-catgirl/runs/pcxfkgosz2e0cb430jk0a/overview)  
+2. [Second Fine-tuning](https://swanlab.cn/@shadow01a/qwen-catgirl/runs/iuou1xratkvbiv7jxw16k/overview)  
+3. [Third Fine-tuning](https://swanlab.cn/@shadow01a/qwen-catgirl/runs/9i2l4mc5qevmnlx2h51m0/overview)  
+
+---
+
+## Evaluation  
+
+Due to the model's unique characteristics, we employed **human evaluation** for daily conversations and **DeepSeek-R1 scoring** (with reference answers provided in advance) for other domains to ensure character consistency and response validity.  
+
+### Key Improvements (vs. internal test models "0501" and "0531-test-all"):  
+- **Stronger detail-awareness** in casual dialogue  
+- **More coherent storytelling** in creative tasks  
+- **Deeper reasoning** during thinking mode  
+- **Better persona adherence** in long-form conversations without explicit prompts  
+- **Significant gains** in math/code domains (internal 20-question benchmark):  
+
+| Model | Math (Single Attempt) | Code (Single Attempt) |  
+|-------|-----------------------|-----------------------|  
+| Internal Test Model-0501 | 10% | 0% |  
+| DeepSeek-R1-0528-Qwen3-8B-Catgirl-0531-test-all | 30% | 20% |  
+| **DeepSeek-R1-0528-Qwen3-8B-Catgirl-v2.5** | **70%** | **60%** |  
+
+---
+
+## Usage Guidelines  
+
+### Recommended Parameters:  
+- `temperature`: 0.7 (reasoning mode) / 0.6 (standard mode)  
+- `top_p`: 0.95  
+
+### Critical Notes:  
+- **Avoid** using model's reasoning chains as conversation context  
+- Inherits base model's tendency for lengthy reasoning in some cases – allow completion even if intermediate steps seem unusual  
+
+### English Mode:  
+Add this system prompt for English responses:  
+```  
+You are a catgirl. Please speak English.  
+```  
+
+---
+
+## Acknowledgments  
+
+Special thanks to:  
+- **LLaMA-Factory** (fine-tuning framework)  
+- **Qwen Team** (base model provider)  
+- **DeepSeek Team** (DeepSeek-R1 evaluation support)