ZPT-Titan-1.2B-Instruct : Title Generation Model

🚀 Overview

ZPT-Titan-1.2B-Instruct is a highly efficient, 1.2 Billion parameter language model specifically fine-tuned for generating concise and descriptive titles from long-form text.

Built upon the robust LiquidAI LFM 2.5 1.2b architecture and specialized training on the agentlans/wikipedia-paragraphs-titles dataset, this model excels at distilling lengthy content into impactful, accurate, and easily readable titles. It is optimized for integration into applications requiring high-quality content indexing, such as chat interfaces and note-taking tools like Open WebUI.

---

🛠️ Technical Specifications

This model is provided in optimized formats for broad compatibility and performance.

Feature	Specification	Details
Model Name	ZPT-Titan-1.2B-Instruct	"Titan" references its specialization in Title Generation.
Base Model	LiquidAI LFM 2.5 1.2b	The foundational architecture.
Training Data	agentlans/wikipedia-paragraphs-titles	Dataset used to fine-tune title extraction skills.
Fine-tuning Framework	Unsloth Studio	Trained 2x faster using the Unsloth optimization techniques.
Model Size	1.2 Billion Parameters	Offers a strong balance of performance and deployment efficiency.
Supported Formats	GGUF, Quantized	Optimized for CPU/GPU inference via llama.cpp.

---

⚙️ Performance & Implementation

The model has been converted and optimized to the GGUF format, allowing for highly efficient local deployment.

Performance Benefits:

• Unsloth Optimization: The training process utilized Unsloth, enabling significantly faster training times and optimized model structure.
• GGUF Efficiency: Quantized files like the included Q8_0 version ensure excellent performance even on resource-constrained hardware.

Available Model Files: The following highly optimized file is available for immediate use:

• LFM2.5-1.2B-Instruct.Q8_0.gguf

---

💡 Use Cases

The primary function of ZPT-Titan-1.2B-Instruct is to act as an advanced summarization component focused purely on titling.

• Chat Interfaces: Automatically generating compelling titles for conversational threads.
• Knowledge Management: Integrating into platforms (e.g., Open WebUI) to auto-title long notes and documents.
• Content Indexing: Creating standardized, concise metadata for massive repositories of text.

---

💻 Installation & Usage

The model is designed to work seamlessly with the llama.cpp ecosystem.

Dependencies:

• llama.cpp (for CPU/GPU inference)
• unsloth (for initial conversion and optimization)

CLI Usage: You can invoke the model using the following command structure. Ensure you have the necessary tool installed.

• Text-Only LLMs:

  llama-cli -hf zmail-tech/ZPT-Titan-1.2B-Instruct --jinja
  

• Multimodal Models:

  llama-mtmd-cli -hf zmail-tech/ZPT-Titan-1.2B-Instruct --jinja
  

---

Note: The model is named Titan to reflect its specialized power and scale in Title Generation. For full setup instructions, please refer to the Unsloth AI GitHub resources.