Instructions to use CineAI/FreeThinker3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CineAI/FreeThinker3B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("CineAI/FreeThinker3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use CineAI/FreeThinker3B with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for CineAI/FreeThinker3B to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for CineAI/FreeThinker3B to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for CineAI/FreeThinker3B to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="CineAI/FreeThinker3B", max_seq_length=2048, )
| base_model: | |
| - unsloth/Llama-3.2-3B-Instruct-bnb-4bit | |
| tags: | |
| - text-generation-inference | |
| - transformers | |
| - unsloth | |
| - llama | |
| - trl | |
| license: apache-2.0 | |
| language: | |
| - en | |
| datasets: | |
| - CineAI/libertarian | |
| # Model Card | |
| The model was fine-tuned using CineAI's own [CineAI/libertarian](https://huggingface.co/datasets/CineAI/libertarian) dataset to determine the closeness of a particular expression, quote, etc. to the ideas of libertarianism and freedom. To test the model, you can use examples generated by ChatGPT-4 or your own. Feel free to make changes to the dataset to improve it, as well as to improve the model. | |
| **Example statements are divided into categories:** | |
| **Libertarian Statements:** | |
| 1. "The government has no right to dictate how individuals spend their money or run their businesses." | |
| 2. "Property rights are the foundation of a free and prosperous society." | |
| 3. "Charity is most effective when it's voluntary, not enforced through taxation." | |
| 4. "True equality is the equality of opportunity, not the equality of outcomes." | |
| 5. "Individuals, not governments, are best equipped to decide what is right for their lives." | |
| **Non-Libertarian Statements:** | |
| 1. "The state must control housing markets to prevent exploitation and ensure affordable living for all." | |
| 2. "Strong government oversight is necessary to keep large corporations in check." | |
| 3. "Redistributing wealth through progressive taxation is the only way to achieve fairness in society." | |
| 4. "Economic planning by the government is essential to prevent market failures." | |
| 5. "Universal healthcare should be fully funded and managed by the government." | |
| **Mixed Statements:** | |
| 1. "Freedom is vital, but it is the government’s responsibility to protect individuals from economic inequality." | |
| 2. "Private ownership drives innovation, but industries like healthcare and education should remain public." | |
| 3. "Free trade is ideal, but tariffs are necessary to protect national industries." | |
| 4. "Taxes should be minimized for individuals, but large corporations must contribute more to the public good." | |
| 5. "Markets regulate themselves well, but environmental protections require government intervention." | |
| # How to use | |
| You can easily interact with the model via [google colab](https://colab.research.google.com/drive/150Dnk9nXuCQnTh-twVRUG9frwmtLjeZv?usp=sharing) | |
| # Uploaded model | |
| - **Developed by:** CineAI | |
| - **License:** apache-2.0 | |
| - **Finetuned from model :** unsloth/llama-3.2-3b-instruct-bnb-4bit | |
| This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. | |
| [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |