Update README.md

README.md

@@ -41,7 +41,7 @@ quantization:
 - **Developed by:** 8lianno  
 - **Model type:** Causal Language Model (Llama-based, instruction-tuned)  
 - **Language:** Persian (fa)  
-- **License:** *[More Information Needed]*  
+- **License:** MIT (Dedicated Model For Matrix AI)
 - **Finetuned from:** `meta-llama/Llama-3.1-8B-Instruct`
 
 This model has been trained to understand Persian poetic structure, using additional tokens `[شروع_شعر]`, `[پایان_شعر]`, and `[مصرع]` to guide and maintain poem formatting. It can respond to various thematic prompts—whether about nature, love, historical figures, or abstract concepts—and produce a poem that attempts to follow Persian poetry norms.
@@ -49,8 +49,7 @@ This model has been trained to understand Persian poetic structure, using additi
 ### Model Sources
 
 - **Repository:** [https://huggingface.co/8lianno/llama_poetry_fa](https://huggingface.co/8lianno/llama_poetry_fa)  
-- **Paper [optional]:** No formal paper at this time.  
-- **Demo [optional]:** Future demonstration pages may be provided.
+- **Paper [optional]:** No paper at this time.  
 
 ## Uses
 
@@ -60,7 +59,32 @@ This model is intended to generate Persian poetry in response to user prompts. I
 
 **Example:**
 - **Prompt:** "درباره بهار شعری بسرایید"  
-- **Response:** A poem about spring, attempting to maintain poetic structure and rhyme.
+- **Response:**
+  -  عشق چون بهار به جان می افروزد
+  -  هر دم به گلستان دل می روزند
+  -  در شب سیاه، چون شمع می تابد
+  -  هر دم به عشق، جان می روزند
+
+- **Prompt:** "درباره دریا شعری بسرایید"  
+- **Response:**
+  -  دریا آینه‌ی آسمان است
+  -  در سینه‌ی او، راز نهان است
+  -  هر موج او به ساحل می‌رسد
+  -  صد قصه‌ی عشق و غم و جان است
+
+- **Prompt:** "درباره عشق بنویسید"  
+- **Response:**
+  -  امید چراغ راه بود
+  -  در ظلمت شب تاب بود
+  -  هر کس که با امید همره بود
+  -  صاحب گنج بی‌بند و بست بود
+
+- **Prompt:** "آسمان چرا می گرید؟"  
+- **Response:**
+  -  آسمان ز عشق میگرید
+  -  از غم خورشید میگرید
+  -  هر کس که به دل عاشق شد
+  -  صد بهار در دل میگرید
 
 ### Downstream Use
 
@@ -83,12 +107,13 @@ The model’s content is drawn from its training data and may reflect certain cu
 - Struggle with modern or colloquial Persian forms.
 - Occasionally produce incoherent or repetitive verses.
 
-Users should critically evaluate the generated text, especially if used in academic or public-facing contexts.
+Users should critically evaluate the generated text, especially if used in public-facing contexts.
 
 ### Recommendations
 
 - Review generated poems for cultural appropriateness.
 - Verify factual accuracy independently.
+- Suggested for Indirect and Poetic answers.
 - For sensitive or controversial topics, consider human moderation.
 
 ## How to Get Started with the Model