Update README.md

README.md

@@ -21,9 +21,10 @@ language:
 
 
 
-# kallamni-1.2b-v1m
+# kallamni-1.2b-v1
+<img src="banner.png" width="800" />
 
-**Kallamni 1.2B v1m** is a **1.2B parameter Arabic conversational model** fine-tuned specifically for **spoken Emirati Arabic (اللهجة الإماراتية المحكية)**.
+**Kallamni 1.2B v1** is a **1.2B parameter Arabic conversational model** fine-tuned specifically for **spoken Emirati Arabic (اللهجة الإماراتية المحكية)**.
 It is designed to generate **natural, fluent, and culturally relevant** responses for daily-life conversations, rather than formal Modern Standard Arabic (MSA).
 
 ---
@@ -41,7 +42,7 @@ It is designed to generate **natural, fluent, and culturally relevant** response
 ## Dataset
 
 * **Size:** 12,324 examples.
-* **Source:** Synthetic Q\&A pairs created via GPT-5 + GPT-4o, filtered for Emirati dialect.
+* **Source:** Synthetic Q\&A pairs created via GPT-5 + GPT-4o, Emirati dialect.
 * **Domains covered:**
 
   * Daily life conversations (shopping, weather, greetings, family, transport).
@@ -81,7 +82,7 @@ You can load and run the model with `transformers`:
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Load model and tokenizer
-model_id = "yasserrmd/kallamni-1.2b-v1m"
+model_id = "yasserrmd/kallamni-1.2b-v1"
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",
@@ -152,4 +153,7 @@ print(tokenizer.decode(output[0], skip_special_tokens=False))
 
 * **Unsloth** team for efficient fine-tuning tooling.
 * **TRL** from Hugging Face for alignment training.
-* Synthetic dataset generation powered by **GPT-5** and **GPT-4o**.
+* Synthetic dataset generation powered by **GPT-5** and **GPT-4o**.
+* **Liquid AI** for innovative open-weight model releases that inspired experimentation.
+
+