SkGufranAhmed/functiongemma-finetuned

This model is a fine-tuned version of [google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it).

It has been further trained using Supervised Fine-Tuning (SFT) via the TRL framework to enhance its performance on specific instruction-following and function-calling tasks.

Uploaded by: SkGufranAhmed

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="SkGufranAhmed/functiongemma-finetuned", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with the SFT (Supervised Fine-Tuning) method to better align with user instructions and structured output formats.

Framework versions

• —TRL: 1.8.0
• —Transformers: 5.12.1
• —Pytorch: 2.11.0+cu128
• —Datasets: 5.0.0
• —Tokenizers: 0.22.2

Usage Warnings

🚨 CRITICAL: Please read before deploying. 🚨

• —Fine-Tuned Behavior: While the base model (FunctionGemma) includes safety mechanisms, fine-tuning can shift outputs. Users should rigorously review generated content, especially in production environments.
• —Experimental Use: This model is recommended for research, testing, or controlled environments. Avoid direct use in public-facing applications without thorough evaluation.
• —User Responsibility: You are solely responsible for ensuring that your usage of this model complies with all applicable laws and ethical guidelines.
• —No Guarantees: The uploader (SkGufranAhmed) and the original developers bear no responsibility for any consequences arising from the use of this fine-tuned model.

Donations & Follow

If you find this model useful, please consider supporting my work!

• —⭐ Follow me on Hugging Face: SkGufranAhmed to stay updated on my latest models and quantizations!
• —Follow the original base model updates from Google.

Your support helps me continue training, fine-tuning, and quantizing new models. Even a cup of coffee can make a huge difference!

• —Bitcoin (BTC):

  bc1qt3lwtpeeg5ldsjj8yw7kjrqe6c89csm68wwn64

• —Support me on Whop(Donate): https://whop.com/@skgufranahmed/

Citations

Cite TRL as:

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}