Update README.md

README.md

@@ -11,81 +11,137 @@ tags:
 - trl
 - sft
 ---
-Indian Legal Assistant: A LLaMA-based Model for Indian Legal Text Generation
-This repository contains information and code for the Indian Legal Assistant, a LLaMA-based model finetuned on Indian legal texts. The model is designed to assist with various legal tasks and queries related to Indian law.
-
-Table of Contents
-Model Description
-Model Details
-Installation
-Usage
-Evaluation
-Contributing
-License
-Model Description
-The Indian Legal Assistant is a text generation model specifically trained to understand and generate text related to Indian law. It is suitable for various legal tasks such as:
-
-Legal question answering
-Case summarization
-Legal document analysis
-Statute interpretation
-Model Details
-Model Name: Indian_Legal_Assistant
-Developer: varma007ut
-Model Size: 8.03B parameters
-Architecture: LLaMA
-Language: English
-License: Apache 2.0
-Hugging Face Repository: varma007ut/Indian_Legal_Assistant
-Installation
-To use this model, install the required libraries:
-
-bash
-Copy code
+# Indian Legal Assistant: A LLaMA-based Model for Indian Legal Text Generation
+
+This repository contains information and code for using the Indian Legal Assistant, a LLaMA-based model finetuned on Indian legal texts. This model is designed to assist with various legal tasks and queries related to Indian law.
+
+## Table of Contents
+
+- [Model Description](https://www.notion.so/1030d0a0ba4180268747e79df12fd2d5?pvs=21)
+- [Model Details](https://www.notion.so/1030d0a0ba4180268747e79df12fd2d5?pvs=21)
+- [Installation](https://www.notion.so/1030d0a0ba4180268747e79df12fd2d5?pvs=21)
+- [Usage](https://www.notion.so/1030d0a0ba4180268747e79df12fd2d5?pvs=21)
+- [Evaluation](https://www.notion.so/1030d0a0ba4180268747e79df12fd2d5?pvs=21)
+- [Contributing](https://www.notion.so/1030d0a0ba4180268747e79df12fd2d5?pvs=21)
+- [License](https://www.notion.so/1030d0a0ba4180268747e79df12fd2d5?pvs=21)
+
+## Model Description
+
+The Indian Legal Assistant is a text generation model specifically trained to understand and generate text related to Indian law. It can be used for tasks such as:
+
+- Legal question answering
+- Case summarization
+- Legal document analysis
+- Statute interpretation
+
+## Model Details
+
+| Attribute | Value |
+| --- | --- |
+| Model Name | Indian_Legal_Assitant |
+| Developer | varma007ut |
+| Model Size | 8.03B parameters |
+| Architecture | LLaMA |
+| Language | English |
+| License | Apache 2.0 |
+| Hugging Face Repo | [varma007ut/Indian_Legal_Assitant](https://huggingface.co/varma007ut/Indian_Legal_Assitant) |
+
+## Installation
+
+To use this model, you'll need to install the required libraries:
+
+```bash
 pip install transformers torch
 # For GGUF support
 pip install llama-cpp-python
-Usage
+
+```
+
+## Usage
+
 There are several ways to use the Indian Legal Assistant model:
 
-1. Using Hugging Face Pipeline
-python
-Copy code
+### 1. Using Hugging Face Pipeline
+
+```python
 from transformers import pipeline
 
-pipe = pipeline("text-generation", model="varma007ut/Indian_Legal_Assistant")
+pipe = pipeline("text-generation", model="varma007ut/Indian_Legal_Assitant")
 
 prompt = "Summarize the key points of the Indian Contract Act, 1872:"
 result = pipe(prompt, max_length=200)
 print(result[0]['generated_text'])
-2. Using Hugging Face Transformers Directly
-python
-Copy code
+
+```
+
+### 2. Using Hugging Face Transformers directly
+
+```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("varma007ut/Indian_Legal_Assistant")
-model = AutoModelForCausalLM.from_pretrained("varma007ut/Indian_Legal_Assistant")
+tokenizer = AutoTokenizer.from_pretrained("varma007ut/Indian_Legal_Assitant")
+model = AutoModelForCausalLM.from_pretrained("varma007ut/Indian_Legal_Assitant")
 
 prompt = "What are the fundamental rights in the Indian Constitution?"
 inputs = tokenizer(prompt, return_tensors="pt")
 outputs = model.generate(**inputs, max_length=200)
 print(tokenizer.decode(outputs[0]))
-3. Using GGUF Format with llama-cpp-python
-python
-Copy code
+
+```
+
+### 3. Using GGUF format with llama-cpp-python
+
+```python
 from llama_cpp import Llama
 
 llm = Llama.from_pretrained(
-    repo_id="varma007ut/Indian_Legal_Assistant",
+    repo_id="varma007ut/Indian_Legal_Assitant",
     filename="ggml-model-q4_0.gguf",  # Replace with the actual GGUF filename if different
 )
 
 response = llm.create_chat_completion(
-    messages=[
-        {"role": "user", "content": "Explain the concept of judicial review in India."}
+    messages = [
+        {
+            "role": "user",
+            "content": "Explain the concept of judicial review in India."
+        }
     ]
 )
 
 print(response['choices'][0]['message']['content'])
-4. Using Inference Endpoints
-This model supports Hugging Face Inference Endpoints. You can deploy the model and use it via API calls. Refer to the Hugging Face documentation for more information on setting up and using Inference Endpoints.
+
+```
+
+### 4. Using Inference Endpoints
+
+This model supports Hugging Face Inference Endpoints. You can deploy the model and use it via API calls. Refer to the [Hugging Face documentation](https://huggingface.co/docs/inference-endpoints/index) for more information on setting up and using Inference Endpoints.
+
+## Evaluation
+
+To evaluate the model's performance:
+
+1. Prepare a test set of Indian legal queries or tasks.
+2. Use standard NLP evaluation metrics such as perplexity, BLEU score, or task-specific metrics.
+
+Example using BLEU score:
+
+```python
+from datasets import load_metric
+
+bleu = load_metric("bleu")
+predictions = model.generate(encoded_input)
+results = bleu.compute(predictions=predictions, references=references)
+
+```
+
+## Contributing
+
+We welcome contributions to improve the model or extend its capabilities. Please see our [Contributing Guidelines](https://www.notion.so/CONTRIBUTING.md) for more details.
+
+## License
+
+This project is licensed under the Apache 2.0 License. See the [LICENSE](https://www.notion.so/LICENSE) file for details.
+
+---
+
+**Note:** While this model is based on the LLaMA architecture, it has been finetuned on Indian legal texts. Ensure compliance with all relevant licenses and terms of use when using this model.