Update README.md

README.md

@@ -40,9 +40,85 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
+```
+TEXT = """
+
+"""
+
+SCHEMA = """
+
+"""
+
+SYSTEM_PROMPT = """
+### Role:
+You are an expert data extractor specializing in mapping hierarchical text data into a given JSON Schema.
+
+### DATA INPUT:
+- **Text:** ```{{TEXT}}```  
+- **Empty JSON Schema:** ```{{SCHEMA}}```  
+
+### TASK REQUIREMENT:
+1. Analyze the given text and map all relevant information strictly into the provided JSON Schema.
+2. Provide your output in **two mandatory sections**:
+   - **`<answer>`:** The filled JSON object  
+   - **`<think>`:** Reasoning for the mapping decisions  
+
+### OUTPUT STRUCTURE:
+
+`<think> /* Explanation of mapping logic */ </think>`
+`<answer> /* Completed JSON Object */ </answer>`
+
+### STRICT RULES FOR GENERATING OUTPUT:
+1. **Both Tags Required:**  
+   - Always provide both the `<think>` and the `<answer>` sections.  
+   - If reasoning is minimal, state: "Direct mapping from text to schema."
+2. **JSON Schema Mapping:**  
+   - Strictly map the text data to the given JSON Schema without modification or omissions.
+3. **Hierarchy Preservation:**  
+   - Maintain proper parent-child relationships and follow the schema's hierarchical structure.
+4. **Correct Mapping of Attributes:**  
+   -Map key attributes, including `displayName`, `description`, `type`, `component`, and source to define the structure, metadata, and data sources for each field within the schema
+5. **JSON Format Compliance:**  
+   - Escape quotes (`\"`), replace newlines with `\\n`, avoid trailing commas, and use double quotes exclusively.
+6. **Step-by-Step Reasoning:**  
+   - Explain your reasoning within the `<think>` tag.
+
+### IMPORTANT:
+If either the `<think>` or `<answer>` tags is missing, the response will be considered incomplete.
+"""
+from jinja2 import Template
+system_prompt_template = Template(SYSTEM_PROMPT)
+system_prompt_str = system_prompt_template.render(TEXT=TEXT, SCHEMA=SCHEMA)
+```
+
+```
+from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer, FineGrainedFP8Config
+import torch
+
+model_name = "Isotonic/DR1-1.5b-JSON_extraction"
+
+# Initialize tokenizer and model
+device = "mps"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map=device)
+
+inputs = tokenizer([system_prompt_str], return_tensors="pt").to(device)
+text_streamer = TextStreamer(tokenizer)
+
+with torch.no_grad():
+    output_ids = model.generate(
+        input_ids=inputs["input_ids"],
+        attention_mask=inputs["attention_mask"],
+        max_new_tokens=4096,
+        temperature=0.6,
+        top_p=0.92,
+        repetition_penalty=1.1,
+        streamer=text_streamer,
+        pad_token_id=tokenizer.pad_token_id,
+    )
+
+print(tokenizer.decode(output_ids[0], skip_special_tokens=True))
+```
 
 ### Downstream Use [optional]