Update README.md

README.md

@@ -15,9 +15,7 @@ This is a LoRA fine-tuned version of the `Qwen/Qwen3-1.7B` model, specifically t
 
 **Developed by:** Mohammed Orabi
 
-**Funded by \[optional]:** N/A
-
-**Shared by \[optional]:** mohammed-orabi2
+**Shared by :** mohammed-orabi2
 
 **Model type:** Causal Language Model with LoRA adaptation
 
@@ -25,9 +23,9 @@ This is a LoRA fine-tuned version of the `Qwen/Qwen3-1.7B` model, specifically t
 
 **License:** Apache 2.0 (inherits from Qwen3-1.7B)
 
-**Finetuned from model \[optional]:** Qwen/Qwen3-1.7B
+**Finetuned from model :** Qwen/Qwen3-1.7B
 
-**Model Sources \[optional]**
+**Model Sources **
 **Repository:** [https://huggingface.co/mohammed-orabi2/qwen-poetry-lora2](https://huggingface.co/mohammed-orabi2/qwen-poetry-lora2)
 
 
@@ -38,7 +36,7 @@ This is a LoRA fine-tuned version of the `Qwen/Qwen3-1.7B` model, specifically t
 **Direct Use:**
 This model can be used for generating Arabic poetry in response to user queries, particularly in cultural, educational, or creative chatbot applications.
 
-**Downstream Use \[optional]:**
+**Downstream Use :**
 
 * Poetry recommendation systems
 * Arabic literature generation tools
@@ -96,7 +94,7 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 **Training Data:**
 1,000 synthetic Arabic poetic dialogues (prompt + poetic response) generated programmatically.
 
-**Preprocessing \[optional]:**
+**Preprocessing :**
 
 * Applied Qwen chat template
 * Tokenized using Qwen3-1.7B tokenizer with padding/truncation
@@ -109,7 +107,7 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 * Learning rate: 2e-4
 * LoRA config: r=8, alpha=16, dropout=0.05, target: \["q\_proj", "v\_proj"]
 
-**Speeds, Sizes, Times \[optional]:**
+**Speeds, Sizes, Times :**
 
 * Training time: \~24 minutes on L4 GPU
 * Model size: LoRA adapter \~100MB
@@ -155,7 +153,7 @@ Output behavior consistent with training intent. Performs well within poetic use
 
 ---
 
-## Technical Specifications \[optional]
+## Technical Specifications 
 
 **Model Architecture and Objective:** Transformer decoder (CausalLM) + LoRA injection
 
@@ -171,7 +169,7 @@ Output behavior consistent with training intent. Performs well within poetic use
 
 ---
 
-## Citation \[optional]
+## Citation 
 
 **BibTeX:**
 
@@ -189,18 +187,18 @@ Mohammed Orabi. (2025). *Qwen Arabic Poetry LoRA* \[Model]. Hugging Face. [https
 
 ---
 
-## Glossary \[optional]
+## Glossary 
 
 * **LoRA**: Low-Rank Adaptation, a method for efficient model fine-tuning
 * **CausalLM**: Causal Language Modeling, predicts the next token in a sequence
 
 ---
 
-## More Information \[optional]
+## More Information 
 
 For support or feedback, please open an issue on the Hugging Face repo or contact via Hugging Face profile.
 
-## Model Card Authors \[optional]
+## Model Card Authors
 
 Mohammed Orabi