Update README.md

README.md

@@ -6,4 +6,71 @@ tags:
 - llama-factory
 - full
 - generated_from_trainer
----
+---
+
+
+# PsyLLM — Model Card (简版)
+
+**模型名称**：PsyLLM
+**基础模型**：Qwen3-8B
+**训练数据**：[OpenR1-Psy](https://huggingface.co/datasets/GMLHUHE/OpenR1-Psy)
+**训练框架**：LLaMA-Factory
+**训练方式**：全量微调 (Full Fine-tuning)
+
+---
+
+PsyLLM 是一个基于 Qwen3-8B 的心理支持与共情对话模型，使用 [OpenR1-Psy](https://huggingface.co/datasets/GMLHUHE/OpenR1-Psy) 数据集全量微调，旨在提升模型的情绪识别、共情表达与安全提示能力。该模型仅供研究与教育用途，不应作为临床诊断或心理治疗工具。
+
+---
+
+## 推理示例代码
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "GMLHUHE/PsyLLM"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# prepare the model input
+prompt = "I have participated in big group sessions before where I was left to find my own safe place, but it hasn't worked for me."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True # 启用思维模式，可选
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=32768
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
+
+# parsing thinking content
+try:
+    # 查找 </think> 标记 (token id: 151668)
+    index = len(output_ids) - output_ids[::-1].index(151668)
+except ValueError:
+    index = 0
+
+thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
+content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
+
+print("thinking content:", thinking_content)
+print("content:", content)
+```
+
+---
+