Tesslate/Tessa-T1-14B

"Landing Page"

Model Overview

Tessa-T1 is an innovative transformer-based React reasoning model, fine-tuned from the powerful Qwen2.5-Coder-14B-Instruct base model. Designed specifically for React frontend development, Tessa-T1 leverages advanced reasoning to autonomously generate well-structured, semantic React components. Its integration into agent systems makes it a powerful tool for automating web interface development and frontend code intelligence.

---

Model Highlights

• React-specific Reasoning: Accurately generates functional and semantic React components.
• Agent Integration: Seamlessly fits into AI-driven coding agents and autonomous frontend systems.
• Context-Aware Generation: Effectively understands and utilizes UI context to provide relevant code solutions.

---

Example Outputs

See examples demonstrating the powerful reasoning and component creation capabilities of Tessa-T1:

AI upload

Virtual Machine Console

Playlist Management

Prompt: "add in a calendar"

---

Use Cases

Recommended Uses

• Automatic Component Generation: Quickly produce React components from textual prompts.
• Agent-based Web Development: Integrate into automated coding systems for faster frontend workflows.
• Frontend Refactoring: Automate the optimization and semantic enhancement of React code.

Limitations

• Focused on React: Limited use outside React.js frameworks.
• Complex State Management: May require manual adjustments for highly dynamic state management scenarios.

---

How to Use

Inference Example

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "smirki/Tessa-T1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name).to("cuda")

prompt = """<|im_start|>user
Create a React component for a user profile card.<|im_end|>
<|im_start|>assistant
<|im_start|>think
"""

inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=1500, do_sample=True, temperature=0.7)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

---

Performance and Evaluation

• Strengths:

  • Strong semantic React component generation.
  • Excellent integration capabilities with agent-based systems.

• Weaknesses:

  • Complex JavaScript logic may require manual post-processing.

---

Technical Specifications

• Architecture: Transformer-based LLM
• Base Model: Qwen2.5-Coder-14B-Instruct
• Precision: bf16 mixed precision, quantized to q8
• Hardware Requirements: Recommended 12GB VRAM
• Software Dependencies:
  • Hugging Face Transformers
  • PyTorch

---

Citation

@misc{smirki_Tessa-T1,
  title={Tessa-T1: React-Focused Reasoning Model for Component Generation},
  author={tesslate},
  year={2025},
  publisher={Hugging Face},
  url={https://huggingface.co/tesslate/Tessa-T1}
}

---

Contact & Community

• Creator: smirki
• Repository & Demo: Coming soon!

Sponsored by vichar ai Huggingface Website