Update README.md

README.md

@@ -1,23 +1,198 @@
 ---
-base_model: Qwen2.5-Coder-32B-Instruct
-tags:
-- text-generation-inference
-- transformers
-- unsloth
-- qwen2
-- trl
-- sft
 license: apache-2.0
+datasets:
+- smirki/UI_REASONING_v1.01
 language:
 - en
+base_model:
+- Qwen/Qwen2.5-Coder-32B-Instruct
+tags:
+- code
+- ui
+- generation
+- uigen
+library_name: transformers
 ---
 
-# Uploaded  model
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/VSplF7AM1PJPzeR9FlDhE.png)
+
+# **Model Card for UIGEN-T1.1**
+
+New and Improved reasoning traces. Better ui generation. Smarter decisions. Better code generation! Trained on a 700+ dataset. 
+USE BUDGET FORCING (putting the word answer or think at the end of the assistant generation to keep generationg more thinking and use 'answer' to write code.)  
+SFT on 1 x H100 for 1 hour.
+
+## **Model Summary**  
+UIGEN-T1.1-Qwen-32B is a **32-billion parameter transformer model** fine-tuned on **Qwen2.5-Coder-32B-Instruct**. It is designed for **reasoning-based UI generation**, leveraging a complex chain-of-thought approach to produce **robust HTML and CSS-based UI components**. Currently, it is limited to **basic applications such as dashboards, landing pages, and sign-up forms**.  
+
+## **Model Details**  
+
+### **Model Description**  
+UIGEN-T1.1-Qwen-32B generates **HTML and CSS-based UI layouts** by reasoning through design principles. While it has a strong **chain-of-thought reasoning process**, it is currently **limited to text-based UI elements and simpler frontend applications**. The model **excels at dashboards, landing pages, and sign-up forms**, but **lacks advanced interactivity** (e.g., JavaScript-heavy functionalities).  
+
+- **Dataset by:** [smirki](https://huggingface.co/smirki)
+- **Developed by:** [smirki](https://huggingface.co/smirki)
+- **Training Procedures and Scripts by:** [smirki](https://huggingface.co/smirki)
+- **Trained by:** [qingy2024](https://huggingface.co/qingy2024)
+- **Model by:** [qingy2024](https://huggingface.co/qingy2024)
+- **Shared by:** [qingy2024](https://huggingface.co/qingy2024)
+- **Model type:** Transformer-based  
+- **Language(s) (NLP):** English  
+- **License:** Apache 2.0  
+- **Finetuned from model:** Qwen/Qwen2.5-Coder-32B-Instruct  
+
+### **Model Sources**  
+- **Repository:** (Will be uploaded to GitHub soon)  
+- **Hosted on:** [Hugging Face](https://huggingface.co/qingy2024)  
+- **Demo:** Coming soon
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/617YL3OlJHflvR63qbA27.png)
+
+
+## **Uses**  
+
+### **Direct Use**  
+- Generates HTML and CSS code for **basic UI elements**  
+- Best suited for **dashboards, landing pages, and sign-up forms**  
+- Requires **manual post-processing** to refine UI outputs  
+- **May require using the word "answer" at the end of the input prompt** to get better inference  
+
+### **Downstream Use (optional)**  
+- Can be fine-tuned further for **specific frontend frameworks (React, Vue, etc.)**  
+- May be integrated into **no-code/low-code UI generation tools**  
+
+### **Out-of-Scope Use**  
+- Not suitable for **complex frontend applications** involving JavaScript-heavy interactions  
+- May not generate **fully production-ready** UI code  
+- **Limited design variety** – biased towards **basic frontend layouts**  
+
+## **Bias, Risks, and Limitations**  
+
+### **Biases**  
+- **Strong bias towards basic frontend design patterns** (may not generate creative or advanced UI layouts)  
+- **May produce repetitive designs** due to limited training scope  
+
+### **Limitations**  
+- **Artifacting issues**: Some outputs may contain formatting artifacts  
+- **Limited generalization**: Performs best in **HTML + CSS UI generation**, but **not robust for complex app logic**  
+- **May require prompt engineering** (e.g., adding "answer" to input for better results)  
+
+## **How to Get Started with the Model**  
+
+### **Example Model Template**  
+```plaintext
+<|im_start|>user
+{question}<|im_end|>
+<|im_start|>assistant
+<|im_start|>think
+{reasoning}<|im_end|>
+<|im_start|>answer
+```
+
+### **Basic Inference Code**  
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "qingy2024/UIGEN-T1.1-Qwen-32B"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name).to("cuda")
+
+prompt = """<|im_start|>user
+Make a dark-themed dashboard for an oil rig.<|im_end|>
+<|im_start|>assistant
+<|im_start|>think
+"""
+
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+outputs = model.generate(**inputs, max_new_tokens=12012, do_sample=True, temperature=0.7) #max tokens has to be greater than 12k
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## **Training Details**  
+
+### **Training Data**  
+- **Based on:** Qwen2.5-Coder-32B-Instruct  
+- **Fine-tuned on:** UI-related datasets with reasoning-based HTML/CSS examples  
+
+### **Training Procedure**  
+- **Preprocessing:** Standard text-tokenization using Hugging Face transformers  
+- **Training Precision:** **bf16 mixed precision**  quantized to q8
+- **Training Method:** Full-precision LoRA for 1 epoch, then merged to 16 bit (this model).
+
+## **Evaluation**  
+
+### **Testing Data, Factors & Metrics**  
+- **Testing Data:** Internal UI design-related datasets  
+- **Evaluation Factors:** Bias towards basic UI components, robustness in reasoning, output quality  
+- **Metrics:** Subjective evaluation based on UI structure, correctness, and usability  
+
+### **Results**  
+- **Strengths:**  
+  - **Good at reasoning-based UI layouts**  
+  - **Generates structured and valid HTML/CSS**  
+- **Weaknesses:**  
+  - **Limited design diversity**  
+  - **Artifacting in outputs**  
+
+## **Technical Specifications**  
+
+### **Model Architecture and Objective**  
+- **Architecture:** Transformer-based LLM fine-tuned for UI reasoning  
+- **Objective:** Generate **robust frontend UI layouts with chain-of-thought reasoning**  
+
+### **Compute Infrastructure**  
+- **Hardware Requirements:** > 24GB VRAM recommended
+- **Software Requirements:**  
+  - Transformers library (Hugging Face)  
+  - PyTorch  
+
+## **Citation**  
+If using this model, please cite:  
+
+**BibTeX:**  
+```bibtex
+@misc{smirki_UIGEN-T1.1,
+  title={UIGEN-T1.1.1: Chain-of-Thought UI Generation Model},
+  author={smirki},
+  year={2025},
+  publisher={Hugging Face},
+  url={https://huggingface.co/smirki/UIGEN-T1.11}
+}
+```
+
+## **More Information**  
+- **GitHub Repository:** (Coming soon)  
+- **Web Demo:** (Coming soon)  
+
+## **Model Card Authors**  
+- **Author:** smirki  
+
+## **Model Card Contact**  
+- **Contact:** [smirki](https://huggingface.co/smirki), [qingy2024 on Hugging Face](https://huggingface.co/smirki)
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/VLs2LyOPXV4GZ2feXpD7F.png)
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/boAgm__7mbD_B37OZzzyw.png)
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/aBn-uzBsmK7vj-CxXRyBi.png)
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/HaPat6448BpqneaBU47bz.png)
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/8VuOPWMSJlu3kxmUQJb6R.png)
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/RgFpQigIYes7wvzulZnkg.png)
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/alBaCYJSLKyomF55XjOv-.png)
 
-- **Developed by:** qingy2024
-- **License:** apache-2.0
-- **Finetuned from model :** Qwen2.5-Coder-32B-Instruct
 
-This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/k3uu2IPU_wIWco45RwdOV.png)
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+---