Tesslate/Tessa-T1-14B

TEXT GENERATIONConcurrency Cost:1Model Size:14.8BQuant:FP8Ctx Length:32kPublished:Mar 24, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Tessa-T1-14B by Tesslate is a 14 billion parameter transformer-based React reasoning model, fine-tuned from Qwen2.5-Coder-14B-Instruct. It is specifically designed to autonomously generate well-structured, semantic React components and integrates seamlessly into AI-driven coding agents. This model excels at context-aware generation for frontend development, providing relevant code solutions for UI contexts.

Loading preview...

Model Overview

Tessa-T1-14B is a specialized transformer-based React reasoning model developed by Tesslate. Fine-tuned from the Qwen2.5-Coder-14B-Instruct base, this model is engineered to autonomously generate semantic React components.

Key Capabilities

  • React-specific Reasoning: Generates functional and semantic React components accurately.
  • Agent Integration: Designed for seamless incorporation into AI-driven coding agents and autonomous frontend systems.
  • Context-Aware Generation: Understands and utilizes UI context to produce relevant code solutions.

Recommended Uses

  • Automatic Component Generation: Quickly creates React components from textual prompts.
  • Agent-based Web Development: Enhances automated coding systems for faster frontend workflows.
  • Frontend Refactoring: Automates optimization and semantic improvements of React code.

Limitations

  • Primarily focused on React.js frameworks, limiting its utility outside this domain.
  • May require manual adjustments for highly dynamic or complex state management scenarios in React applications.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p