Update README.md

README.md

@@ -13,26 +13,23 @@ This model has been pushed to the Hub using the [PytorchModelHubMixin](https://h
 - Docs: [More Information Needed]
 
 
-# [ALIF Base 100M]
+# ALIF Base 100M
 
-**[ALIF Base 100M]** is an Urdu generative language model from the **ALIF الف** series (a Final Year Project at Habib University), developed by **Orature AI**. This model is a [decoder-only Transformer / Naive GPT-2 based] architecture, specifically pretrained for the Urdu language.
+**ALIF Base 100M** is an Urdu generative language model from the **ALIF الف** series (a Final Year Project at Habib University), developed by **Orature AI**.
 
 ## Model Details
 
 *   **Developed by:** Orature AI (S.M Ali Naqvi, Zainab Haider, Haya Fatima, Ali M Asad, Hammad Sajid)
-<!-- *   **Supervised by:** Dr. Abdul Samad (Habib University) -->
+*   **Supervised by:** Dr. Abdul Samad (Habib University)
 *   **Model type:** Decoder-only Transformer, GPT-like
 *   **Variant:** ALIF-Base-100M
 *   **Language(s) (NLP):** Urdu (ur)
 *   **License:** Apache 2.0
-<!-- *   **Finetuned from model (if applicable):** [e.g., `OratureAI/ALIF-Base-1B`] -->
-<!-- *   **Related Models:** Other models in the ALIF الف series by Orature AI. -->
-<!-- *   **Project Repository/Paper:** [Link to ALIF GitHub Repo or Paper arXiv/Website] -->
 * **Architecture:** Transformer (GPT-Based)
 * **Framework:** PyTorch
 * **Tokeniezer:** SentencePiece Custom Tokenizer
 * **Hyperparameters:**:
-    *   **Vocabulary Size:** 20000
+    *   **Vocabulary Size:** 32000
     *   **Embedding Size:** 768
     *   **Attention Heads:** 12
     *   **Layers:** 12 
@@ -66,7 +63,7 @@ print(f"Generated Text: {generated_text}")
 
 ## Model Description
 
-**ALIF Base 100M** is designed to [generate coherent and contextually relevant Urdu text / understand and follow instructions in Urdu]. It leverages a custom Urdu tokenizer trained on the ALIF-Urdu-Corpus and was pretrained on a large corpus of diverse Urdu text.
+**ALIF Base 100M** is designed to generate coherent and contextually relevant Urdu text. It leverages a custom Urdu tokenizer trained on the ALIF-Urdu-Corpus and was pretrained on a large corpus of diverse Urdu text.
 
 **Key Features:**
 *   Optimized for Urdu language nuances.
@@ -81,11 +78,10 @@ print(f"Generated Text: {generated_text}")
 *   **Research:** Base for further research in Urdu NLP, low-resource language modeling.
 *   **Fine-tuning:** Can be fine-tuned for specific downstream tasks like sentiment analysis, summarization, or domain-specific chatbots in Urdu.
 *   **Educational Purposes:** Understanding SLM behavior for Urdu.
-*   **(For Instruct Models):** Conversational AI, Q&A, task completion in Urdu.
-
+*   
 **Limitations:**
 *   The model is primarily trained on Urdu and may not perform well on other languages or code-switched text unless specifically designed for it (e.g., an Ur-En variant).
-*   As a base generative model (especially for non-instruct versions), it may generate plausible-sounding but incorrect or nonsensical information (hallucinations).
+*   As a base generative model, it may generate plausible-sounding but incorrect or nonsensical information (hallucinations).
 *   The model may reflect biases present in the training data. The ALIF-Urdu-Corpus was curated from diverse sources, but biases (e.g., societal, gender, regional) may still exist.
 *   Performance on highly specific or technical domains may be limited without further fine-tuning.
 *   The model does not have real-time knowledge and its information is limited to its training data.