Create README.md

README.md

@@ -0,0 +1,231 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- Qwen/Qwen2.5-Coder-32B-Instruct
+library_name: transformers
+tags:
+- code
+- codeqwen
+- chat
+- qwen
+- qwen-coder
+- html
+- javascript
+- css
+- tailwindcss
+- frontend
+- web-development
+- ViCoder-html-32B-preview
+- ViCoder-html
+- ViCoder
+- ViCoder-html-preview
+- vichar ai labs
+- vichar ai
+- strive ai labs llp
+- strive ai labs
+- vichar.io
+pipeline_tag: text-generation
+---
+
+<p align="center">
+  <a href="https://vichar.io" target="_blank" rel="noopener noreferrer"> <!-- Link the logo -->
+    <img src="https://vichar.s3.ap-south-1.amazonaws.com/vicoder-html-32B.png" width="450" height="200" alt="ViCoder-html-32B-preview Logo" style="display: block; margin-left: auto; margin-right: auto; border-radius: 15px;"/>
+  </a>
+  <h1 align="center" style="color: #2E86C1; margin-top: 15px; margin-bottom: 5px;"> <!-- Added a subtle blue color -->
+    ViCoder-html-32B-preview
+  </h1>
+</p>
+<p align="center" style="font-size: 1.2em;">
+  <b>🚀 A powerful HTML/CSS/JS sketching model powered by <a href="https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct" style="color: #5DADE2;">Qwen2.5-Coder-32B-Instruct</a> 🚀</b> <!-- Slightly lighter blue link -->
+</p>
+<p align="center" style="font-size: 1.0em; color: #555;">
+  <i>Developed by <a href="https://vichar.io" target="_blank" rel="noopener noreferrer" style="color: #5DADE2;">Vichar AI</a> | <a href="https://huggingface.co/VicharAI" style="color: #5DADE2;">Hugging Face Profile</a></i><br/>
+  <span style="font-size: 0.9em; color: #6c757d;">Licensed under Apache 2.0</span>
+</p>
+
+---
+
+### <span style="color: #1ABC9C;">💡 What is ViCoder-html-32B-preview?</span>
+
+**ViCoder-html-32B-preview** is a preview model in the **ViCoder** series from <a href="https://vichar.io" target="_blank" rel="noopener noreferrer">Vichar AI</a> — a line of models specialized in **code generation**. This model focuses specifically on sketching single-page websites, such as landing pages and dashboards, using using:
+
+- 🧠 **HTML** for semantic structure
+- 🎨 **Tailwind CSS** for modern, utility-first styling
+- ⚙️ **JavaScript** for interactivity and basic dynamic behavior
+
+This model is ideal for:
+- **Web Developers:** Quickly scaffolding dashboards or page layouts.
+- **Frontend Engineers:** Prototyping UIs and exploring design variations.
+- **Designers:** Turning textual mockups into initial code sketches.
+- **Educators & Students:** Learning and experimenting with HTML, Tailwind CSS, and JavaScript in a practical context.
+
+> ⚠️ **Note:** This is a **preview** version. It demonstrates core capabilities but is still under active development. A more refined and robust production release is planned. Stay updated via <a href="https://vichar.io" target="_blank" rel="noopener noreferrer">vichar.io</a> or follow <a href="https://huggingface.co/VicharAI">VicharAI on Hugging Face</a>!
+
+---
+
+### <span style="color: #1ABC9C;">🛠️ Model Details</span>
+
+| Property         | Value                                                                                       |
+| :--------------- | :------------------------------------------------------------------------------------------ |
+| **Model Type**   | Code Generation (Instruction-tuned Language Model)                                          |
+| **Base Model**   | [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct)      |
+| **Developed by** | [Vichar AI](https://vichar.io) ([HF Profile](https://huggingface.co/VicharAI))              |
+| **Languages**    | Primarily HTML, Tailwind CSS, JavaScript. Understands English instructions.                 |
+| **Training Data**| Proprietary curated dataset focusing on high-quality web components and pages.               |
+| **License**      | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)                                   |
+| **Library**      | 🤗 Transformers                                                                              |
+| **Contact**      | Visit [vichar.io](https://vichar.io) or use HF Discussions                                  |
+
+---
+
+### <span style="color: #1ABC9C;">🧱 GGUF Quantized Versions</span>
+
+Quantized versions of **ViCoder-html-32B-preview** in GGUF format are available for efficient local inference using [llama.cpp](https://github.com/ggerganov/llama.cpp), [LM Studio](https://lmstudio.ai/), or [Ollama](https://ollama.com/).
+
+You can find them here:
+- 🔗 [GGUF Quantizations on Hugging Face](https://huggingface.co/VicharAI/ViCoder-html-32B-preview-GGUF)
+
+These quantized variants (Q3_K_M, Q4_K_M, Q6_K, Q8_0) are useful for running the model on lower-memory hardware or for embedding in desktop/web applications.
+
+---
+
+### <span style="color: #1ABC9C;">⚡ Example Usage</span>
+
+Use the `transformers` library pipeline for easy text generation. Ensure you have `transformers`, `torch`, and `accelerate` installed.
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+import torch
+
+# Define model ID
+model_id = "VicharAI/ViCoder-html-32B-preview"
+
+# Load tokenizer and model
+# Use bfloat16 for faster inference if your GPU supports it
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16, # Or torch.float16 if bfloat16 is not supported
+    device_map="auto"           # Automatically distribute across available GPUs/CPU
+)
+
+messages = [
+    {"role": "user", "content": "A modern, sleek landing page for a company focusing on open-source LLM solutions"},
+]
+inputs = tokenizer.apply_chat_template(
+    messages,
+    tokenize = True,
+    add_generation_prompt = True,
+    return_tensors = "pt",
+).to("cuda")
+
+from transformers import TextStreamer
+text_streamer = TextStreamer(tokenizer, skip_prompt = True)
+_ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = 16000,
+                   use_cache = True, temperature = 0.7, min_p = 0.1, repetition_penalty=1.1)
+```
+
+---
+
+### <span style="color: #1ABC9C;">✨ Output Sample</span>
+
+
+```html
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <title>Our Love Story - Surprise Website</title>
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <!-- Tailwind CSS CDN -->
+  <script src="https://cdn.tailwindcss.com"></script>
+  <style>
+    /* Custom animation classes */...
+```
+
+*(**Note:** The model aims to generate complete HTML structures with Tailwind classes. Review and adapt generated code as needed.)*
+
+---
+
+### <span style="color: #1ABC9C;">🧪 Evaluation & Limitations</span>
+
+As a **preview** release, this model has undergone initial internal testing focused on:
+
+- **Code Correctness:** Validity of generated HTML, Tailwind CSS classes, and basic JavaScript snippets.
+- **Tailwind CSS Usage:** Adherence to Tailwind's utility-first principles and common patterns.
+- **Component Structure:** Logical organization of HTML elements for typical web components.
+- **Instruction Following:** Ability to understand and implement requirements from the prompt.
+
+**Current Limitations:**
+
+- **No Formal Benchmarks:** Not yet evaluated on standard code generation benchmarks (e.g., HumanEval-X, MBPP).
+- **Complex Logic:** May struggle with complex JavaScript logic, state management, or intricate CSS beyond Tailwind utilities.
+- **Hallucination Risk:** Like all LLMs, it can sometimes generate incorrect, incomplete, or non-optimal code. Always review the output.
+- **Preview Status:** Not recommended for critical production use without thorough validation.
+
+---
+
+### <span style="color: #1ABC9C;">📍 Roadmap</span>
+
+The **ViCoder** series is an ongoing project at <a href="https://vichar.io" target="_blank" rel="noopener noreferrer">Vichar AI</a>. Our current roadmap includes:
+
+- ✅ **ViCoder-html-32B-preview:** Initial public preview release (this model).
+- ⏳ **ViCoder-html-32B (v1.0):** Planned production-ready release with improved training data, fine-tuning, and evaluation.
+- 🚀 **ViCoder-js-32B:** Future model focusing specifically on advanced JavaScript generation (frameworks, logic).
+- 🐍 **ViCoder-python-32B:** Potential companion model for Python backend code generation.
+- 📊 **Benchmarking & Evaluation:** Formal evaluation on relevant code generation benchmarks.
+
+Follow <a href="https://huggingface.co/VicharAI">VicharAI on Hugging Face</a> or check the [Vichar AI website](https://vichar.io) for announcements!
+
+---
+
+### <span style="color: #1ABC9C;">📄 License</span>
+
+This model and its code are licensed under the **Apache License 2.0**. You can find the full license text [here](https://www.apache.org/licenses/LICENSE-2.0).
+
+---
+
+### <span style="color: #1ABC9C;">🙏 Citation</span>
+
+If you use ViCoder-html-32B-preview in your projects, publications, or research, please cite it:
+
+```bibtex
+@misc{vicharai_vicoder_html_32b_preview_2025,
+  title        = {ViCoder-html-32B-preview: A Preview Model for HTML/Tailwind CSS/JavaScript Sketching},
+  author       = {Vichar AI},
+  year         = {2025},
+  publisher    = {Hugging Face},
+  url          = {https://huggingface.co/VicharAI/ViCoder-html-32B-preview},
+  url          = {https://vichar.io}
+}
+```
+
+---
+
+### <span style="color: #1ABC9C;">📬 Get in Touch</span>
+
+We welcome feedback, questions, and collaboration ideas!
+
+- **Hugging Face:** Open an issue or start a discussion on the [model page's Community tab](https://huggingface.co/VicharAI/ViCoder-html-32B-preview/discussions).
+- **Website:** Visit us at [https://vichar.io](https://vichar.io) for more information about Vichar AI and the ViCoder project.
+- **Contact:** Find direct contact methods on the [Vichar AI website](https://vichar.io).
+
+---
+
+### <span style="color: #1ABC9C;">🤝 Acknowledgments</span>
+
+This project builds upon the incredible work of others:
+
+- **SprykAI** for their support during model experimentation phases.
+- The **Qwen Team** at Alibaba Cloud for developing the foundational [Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) model.
+- The **Hugging Face Team** for their platform and libraries (🤗 Transformers, Accelerate,TRL).
+- The broader **open-source AI community** for continuous innovation and shared knowledge.
+- Development efforts by the team at [Vichar AI](https://vichar.io).
+
+---
+
+<p align="center" style="font-size: 1.1em; font-weight: bold; color: #2ECC71;"> <!-- Changed final line color -->
+  💥 This preview is just the start! Explore, build, and stay tuned for the full ViCoder suite from <a href="https://vichar.io" target="_blank" rel="noopener noreferrer" style="color: #27AE60;">Vichar AI</a>! 💥
+</p>