Update README.md

README.md

@@ -9,5 +9,67 @@ datasets:
 - Kedreamix/psychology-10k-Deepseek-R1-zh
 ---
 
-python:
-  def
+# Model Card for DeepSeek-R1-Psychology-COT
+
+## Model Description
+This model is a fine-tuned version of the DeepSeek-R1-Psychology-COT model, designed for specific tasks in the psychology domain using Chain-of-Thought (CoT) reasoning.
+
+## Usage
+
+### Fine-tuning Code Example
+
+Below is the code to fine-tune the model using the `unsloth` and `trl` libraries:
+
+```python
+# Modules for inference
+import unsloth
+from unsloth import FastLanguageModel
+import torch # Import PyTorch
+from trl import SFTTrainer # Trainer for supervised fine-tuning (SFT)
+from unsloth import is_bfloat16_supported # Checks if the hardware supports bfloat16 precision
+# Hugging Face modules
+from transformers import TrainingArguments # Defines training hyperparameters
+from datasets import load_dataset # Lets you load fine-tuning datasets
+
+model_id = "cvGod/DeepSeek-R1-Psychology-COT"
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name=model_id,
+    max_seq_length=2048,
+    dtype=None,
+    load_in_4bit=True,
+    
+)
+
+prompt_style = """以下是一项任务说明，并附带了更详细的背景信息。
+请撰写一个满足完成请求的回复。
+在回答之前，请仔细考虑问题，并创建一个逐步的思考链，以确保逻辑和准确的回答。
+
+### Instruction:
+你是一个专业的心里专家专家,请你根据以下问题回答。
+### Question:
+{}
+### Response:
+{}"""
+EOS_TOKEN = tokenizer.eos_token
+
+question = """我晚上难以入睡，我认为这是因为我对工作感到压力"""
+
+# Load the inference model using FastLanguageModel (Unsloth optimizes for speed)
+FastLanguageModel.for_inference(model)  # Unsloth has 2x faster inference!
+
+# Tokenize the input question with a specific prompt format and move it to the GPU
+inputs = tokenizer([prompt_style.format(question, "")], return_tensors="pt").to("cuda")
+
+# Generate a response using LoRA fine-tuned model with specific parameters
+outputs = model.generate(
+    input_ids=inputs.input_ids,          # Tokenized input IDs
+    attention_mask=inputs.attention_mask, # Attention mask for padding handling
+    max_new_tokens=1024,                  # Maximum length for generated response
+    use_cache=True,                        # Enable cache for efficient generation
+)
+
+# Decode the generated response from tokenized format to readable text
+response = tokenizer.batch_decode(outputs)
+
+# Extract and print only the model's response part after "### Response:"
+print(response[0].split("### Response:")[1])