|
|
--- |
|
|
license: apache-2.0 |
|
|
--- |
|
|
Below is a sample README file for the repository. You can adjust the sections as needed: |
|
|
|
|
|
--- |
|
|
|
|
|
# Qwen2.5-Coder-14B Houdini Vex Functions |
|
|
|
|
|
This repository hosts a fine-tuned version of the **Qwen2.5-Coder-14B** model, optimized specifically for generating Houdini VEX functions. The model has been fine-tuned using Houdini VEX Functions data and is designed to assist developers and technical artists working in Houdini. |
|
|
|
|
|
## Model Details |
|
|
|
|
|
- **Base Model:** Qwen2.5-Coder-14B |
|
|
- **Fine-Tuning:** Finetuned using Houdini VEX Functions data |
|
|
- **Architecture:** qwen2 |
|
|
- **Model Size:** 14.8B parameters |
|
|
- **Quantization:** 8-bit (Q8_0) |
|
|
- **License:** [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) |
|
|
|
|
|
## Features |
|
|
|
|
|
- **Houdini VEX Expertise:** Specially adapted to generate Houdini VEX code. |
|
|
- **Procedural Workflow:** Ideal for creating procedural geometry, effects, and other Houdini-specific functions. |
|
|
- **Efficient Performance:** Utilizes 8-bit quantization for faster inference while maintaining quality. |
|
|
|
|
|
## Installation |
|
|
|
|
|
To use this model, ensure you have the required dependencies installed. You can install the necessary Python packages using pip: |
|
|
|
|
|
```bash |
|
|
pip install transformers torch |
|
|
``` |
|
|
|
|
|
Then, load the model in your Python script as follows: |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
|
|
model_name = "pahaadi/Qwen2.5-Coder-14B-houdini_vex_functions" |
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
|
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True) |
|
|
|
|
|
# Example usage: Generate Houdini VEX code |
|
|
prompt = "Write a Houdini VEX function that creates procedural geometry." |
|
|
inputs = tokenizer(prompt, return_tensors="pt") |
|
|
outputs = model.generate(**inputs, max_length=256) |
|
|
generated_code = tokenizer.decode(outputs[0], skip_special_tokens=True) |
|
|
print(generated_code) |
|
|
``` |
|
|
|
|
|
## Usage |
|
|
|
|
|
This model is tailored for tasks such as: |
|
|
- Generating Houdini VEX functions. |
|
|
- Assisting with procedural generation tasks in Houdini. |
|
|
- Accelerating coding workflows in Houdini-based projects. |
|
|
|
|
|
Feel free to integrate the model into your Houdini pipeline to enhance your creative coding process. |
|
|
|
|
|
## Fine-Tuning and Contributions |
|
|
|
|
|
If you are interested in further fine-tuning this model or adapting it for other Houdini-related tasks, contributions and suggestions are welcome. Please follow the guidelines provided in the [Hugging Face documentation](https://huggingface.co/docs) for model fine-tuning and deployment. |
|
|
|
|
|
## License |
|
|
|
|
|
This model is released under the [Apache-2.0 License](https://www.apache.org/licenses/LICENSE-2.0). |
|
|
|
|
|
## Citation |
|
|
|
|
|
If you use this model in your research or projects, please consider citing it as follows: |
|
|
|
|
|
```bibtex |
|
|
@misc{pahaadi2025qwen2.5, |
|
|
author = {pahaadi}, |
|
|
title = {Qwen2.5-Coder-14B Houdini Vex Functions}, |
|
|
year = {2025}, |
|
|
publisher = {Hugging Face}, |
|
|
url = {https://huggingface.co/pahaadi/Qwen2.5-Coder-14B-houdini_vex_functions} |
|
|
} |
|
|
``` |
|
|
|
|
|
## Acknowledgments |
|
|
|
|
|
Special thanks to the contributors and the Hugging Face community for their continuous support and for providing an open platform for sharing and developing innovative machine learning models. |
|
|
|
|
|
--- |
|
|
|
|
|
This README provides an overview of the model, usage instructions, and additional details that help users understand and integrate the model into their projects. |
