Update README.md

README.md

@@ -1,21 +1,105 @@
 ---
-base_model: unsloth/phi-4-unsloth-bnb-4bit
+license: apache-2.0
+base_model: microsoft/phi-4
 tags:
 - text-generation-inference
 - transformers
 - unsloth
-- llama
-license: apache-2.0
+- phi-4
+- information-extraction
+- ner
+- relation-extraction
+- knowledge-graph
+- slm
+model_creator: FinaPolat
 language:
 - en
 ---
 
-# Uploaded finetuned  model
+# Phi-4-AdaptableIE: Efficient & Privacy-Preserving Knowledge Graph Extraction
+
+Phi-4-AdaptableIE is a specialized **14.7B parameter Small Language Model (SLM)** optimized via **Supervised Fine-Tuning (SFT)** for high-precision, **Joint Named Entity Recognition (NER) and Relation Extraction (RE)**. 
+
+Unlike traditional multi-stage pipelines that are prone to cascading error propagation, this model performs entity identification and relational mapping in a single cohesive pass. It is designed to be **ontology-adaptive**, allowing it to conform to dynamic, unseen schemas at inference time through a specialized **Structured Prompt Architecture**.
+
+
+
+## 🚀 Model Highlights
+- **Joint Extraction:** Unified NER + RE reducing pipeline complexity.
+- **Ontology-Adaptive:** Zero-shot adaptation to diverse domains (Astronomy, Music, Healthcare, etc.) via dynamic schema variables.
+- **Local & Private:** Optimized for **local CPU-only inference** (via GGUF/Ollama), ensuring data sovereignty without external API dependencies.
+- **Instruction Aligned:** Fine-tuned to follow strict negative constraints, ensuring zero conversational filler in outputs.
+
+## 🛠 Methodology
+The model was fine-tuned using **QLoRA** on the **WebNLG** subset of the **Text2KGBench** benchmark. The training process focused on **Conversational Alignment**, ensuring the model treats extraction as a strict logical mapping:
+`Prompt = f(task, schema, example, text)`
+
+---
+
+## 📝 Prompting Strategy
+To achieve high-fidelity extraction, the model requires a specific prompt structure.
+
+### 1. System Prompt
+```json
+{
+  "role": "system",
+  "content": "You are a helpful AI assistant specializing in Information Extraction tasks such as Named Entity Recognition and Relation Extraction. Follow the instructions given by the user."
+}
+
+### 2. User Prompt Template
+
+Information Extraction is the process of automatically identifying and extracting structured information from unstructured text data... [Context] ...
+Always extract numbers, dates, and currency values regardless of the specific task.
+
+The task at hand is {task}.
+
+Here is an example of task execution:
+{example}
+
+Analyze the text and targets carefully, identify relevant information.
+Extract the information in the following format: `{output_format}`. 
+If no matching entities are found, return an empty list: []. 
+Please provide only the extracted information without any explanations.
+
+Schema: {schema}
+Text: {inputs}
+
+💻 Usage Examples
+Option 1: Transformers (Single GPU)
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "FinaPolat/phi4_adaptableIE_v2"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True)
+
+task = "Joint NER and RE"
+schema = "['CelestialBody', 'apoapsis', 'averageSpeed']"
+inputs = "(19255) 1994 VK8 has an average speed of 4.56 km per second."
+output_format = "[('subject', 'predicate', 'object')]"
+
+prompt = f"Task: {task}\nSchema: {schema}\nText: {inputs}\nExtract:"
+
+input_ids = tokenizer(prompt, return_tensors="pt").to("cuda")
+outputs = model.generate(**input_ids, max_new_tokens=256, temperature=0.0)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
+
+Option 2: High-Throughput Batch Inference (vLLM)
+
+from vllm import LLM, SamplingParams
 
-- **Developed by:** FinaPolat
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/phi-4-unsloth-bnb-4bit
+llm = LLM(
+    model="FinaPolat/phi4_adaptableIE_v2",
+    dtype="bfloat16",
+    trust_remote_code=True,
+    gpu_memory_utilization=0.9,
+    max_model_len=3000,
+    enforce_eager=True, 
+    distributed_executor_backend="uni" 
+)
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+sampling_params = SamplingParams(temperature=0.0, max_tokens=256)
+outputs = llm.chat(batch_prompts, sampling_params=sampling_params, use_tqdm=True)
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+📦 Deployment & Hardware RequirementsDeployment ModeQuantizationHardware RequirementTarget LatencyServer-sideBF161x NVIDIA A100/RTX 4090 (24GB+)Ultra-LowLocal Consumer4-bit GGUF16GB RAM (Apple Silicon / PC CPU)ModerateFor CPU-only local execution, refer to the GGUF version: phi4_adaptableIE_v2-gguf📜 Citation & CreditsIf you use this model in your research, please cite the Text2KGBench framework and the Microsoft Phi-4 technical report.[Link to your Demo Paper or GitHub Repo]