Instructions to use Tesslate/Tessa-T1-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tesslate/Tessa-T1-7B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Tesslate/Tessa-T1-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tesslate/Tessa-T1-7B")
model = AutoModelForCausalLM.from_pretrained("Tesslate/Tessa-T1-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Tesslate/Tessa-T1-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tesslate/Tessa-T1-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tesslate/Tessa-T1-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tesslate/Tessa-T1-7B

SGLang

How to use Tesslate/Tessa-T1-7B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Tesslate/Tessa-T1-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tesslate/Tessa-T1-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Tesslate/Tessa-T1-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tesslate/Tessa-T1-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Tesslate/Tessa-T1-7B with Docker Model Runner:
```
docker model run hf.co/Tesslate/Tessa-T1-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

"Landing Page"

Model Overview

Tessa-T1 is an innovative transformer-based React reasoning model, fine-tuned from the powerful Qwen2.5-Coder-7B-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-7B-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}
}