Update README.md

README.md

@@ -1,63 +1,51 @@
-# 🫐 BerryAI
-
-BerryAI is a multimodal, coding-focused chatbot trained on a mixture of conversational, coding, UI design, and math reasoning datasets.  
-It blends creative dialogue with factual accuracy and programming skill.
-
 ---
-
-## 🚀 Features
-- 💬 Conversational: Fine-tuned with UltraChat for engaging responses  
-- 🧠 Smart: FineWeb improves general knowledge  
-- 🧮 Reasoning: OpenWebMath for step-by-step logic  
-- 💻 Coder: WizardCoderData, StarCoderData, and DS-Coder-Instruct for deeper programming skill  
-- 🎨 UI Genius: Trained on multiple UI/UX datasets for design insights
-
+language:
+- en
+library_name: transformers
+license: mit
+tags:
+- coding
+- ui
+- chat
+- math
+- factual
+- agent
+datasets:
+- hotboxxgenn/mix-openhermes-openorca-platypus-airoboros-chatalpaca-opencode
+- microsoft/rStar-Coder
+- ed001/ds-coder-instruct-v1
+- bigcode/starcoderdata
+- bigcode/starcoder2data-extras
+- codeparrot/self-instruct-starcoder
+- mrtoy/mobile-ui-design
+- YashJain/UI-Elements-Detection-Dataset
+- tecky-tech/Tecky-UI-Elements-VLM
+- Tesslate/UIGEN-T2
+- FineWeb
+- OpenWebMath
+- UltraChat
+- WizardCoderData
+base_model:
+- mistralai/Mixtral-8x7B-v0.1
+- OpenBuddy/openbuddy-openllama-7b-v12-bf16
+- HuggingFaceH4/mistral-7b-grok
+- togethercomputer/RedPajama-INCITE-7B-Chat
 ---
 
-## 🧰 Base Models
-- `mistralai/Mixtral-8x7B-v0.1`  
-- `OpenBuddy/openbuddy-openllama-7b-v12-bf16`  
-- `HuggingFaceH4/mistral-7b-grok`  
-- `togethercomputer/RedPajama-INCITE-7B-Chat`
+# 🧠 UltraCode UI Chatbot (v1.1)
 
----
-
-## 📚 Datasets
-- hotboxxgenn/mix-openhermes-openorca-platypus-airoboros-chatalpaca-opencode  
-- microsoft/rStar-Coder  
-- ed001/ds-coder-instruct-v1  
-- bigcode/starcoderdata  
-- bigcode/starcoder2data-extras  
-- codeparrot/self-instruct-starcoder  
-- mrtoy/mobile-ui-design  
-- YashJain/UI-Elements-Detection-Dataset  
-- tecky-tech/Tecky-UI-Elements-VLM  
-- Tesslate/UIGEN-T2  
-- FineWeb  
-- OpenWebMath  
-- UltraChat  
-- WizardCoderData  
+**UltraCode** is a multi-skill conversational AI designed for **coding**, **UI generation**, **math reasoning**, and **factual grounding**.  
+It merges top open-source instruction datasets to deliver a balanced, high-utility assistant suitable for developers, designers, and learners.
 
 ---
 
-## 🧠 Capabilities
-✅ Coding (Python, C#, JavaScript)  
-✅ UI Design Advice (Mobile / Web)  
-✅ Conversational + Creative Writing  
-✅ Factual Knowledge  
-✅ Math & Logic Reasoning
+## 🚀 Skills
+- 💻 **Coding:** Python, C#, JavaScript, React, Tailwind, API generation
+- 🎨 **UI Generation:** Responsive layouts, component design, mobile UI
+- 💬 **Conversational Flair:** Engaging and context-aware
+- 🧮 **Math Reasoning:** Solves equations and explains steps
+- 🌐 **Factual Grounding:** Improves accuracy and reduces hallucination
 
 ---
 
-## ⚡ Usage
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model_id = "hotboxxgenn/BerryAI"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
-
-prompt = "Write a C# function that scrapes titles from a webpage."
-inputs = tokenizer(prompt, return_tensors="pt")
-outputs = model.generate(**inputs, max_new_tokens=250)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+## 🧩