README.md

---
license: other
license_name: mocha
license_link: LICENSE
datasets:
- theguywhosucks/mocha
language:
- en
pipeline_tag: text-generation
tags:
- english
- composition
- sentance_completion
---

# Mocha ☕

Mocha is a **sentence completion model** designed for lightweight, fast, and creative text generation.
Built with efficiency in mind, Mocha allows you to integrate natural language completion into your projects without the overhead of larger models.

<p align="center">
  <img src="./banner.png" alt="Mocha Banner" width="600"/>
</p>

---

## 🔥 Features

* ⚡ **Lightweight** – optimized for speed and deployment.
* 📝 **Sentence Completion** – generate contextually relevant endings for text prompts.
* 📦 **Safetensors Format** – stored in `.safetensors` for secure and efficient loading.

---

## 📂 Project Structure

```
.
├── mocha.safetensors # The model weights
├── config.json
├── generation_config.json
├── itos.json
├── stoi.json
├── logo.png          # Project logo
├── banner.png        # Project banner
└── README.md
```

---

## 🚀 Usage

You can load Mocha with [🤗 Transformers](https://github.com/huggingface/transformers) and [safetensors](https://github.com/huggingface/safetensors):

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("theguywhosucks/Mocha")
model = AutoModelForCausalLM.from_pretrained(
    "theguywhosucks/Mocha",
    torch_dtype=torch.float16
)

# Example usage
prompt = "The future of AI is"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)

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

---

## 📸 Assets

<p align="center">
  <img src="./logo.png" alt="Mocha Logo" width="120"/>
</p>

---

## 🛠️ Requirements

* Python 3.9+
* [Transformers](https://pypi.org/project/transformers/)
* [Safetensors](https://pypi.org/project/safetensors/)
* [PyTorch](https://pytorch.org/)

Install dependencies:

```bash
pip install torch transformers safetensors
```

---

## 📜 License

This project is licensed under the **Mocha Proprietary License**.
Usage, distribution, and modification are restricted. Please see the [LICENSE](./LICENSE) file for full details.

---

☕ **Mocha** – lightweight sentence completion made simple.