Modelpublic

hridyansh22/gemma-3-finetune

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

0likes30downloads

Model Card

Uploaded finetuned model

Developed by: hridyansh22 License: apache-2.0 Finetuned from model: `unsloth/gemma-3-1b-it-unsloth-bnb-4bit`

This gemma3_text model was trained 2x faster using [Unsloth](https://github.com/unslothai/unsloth) and Hugging Face’s TRL library.

<div align="left"> <img src="https://huggingface.co/datasets/huggingface/brand-assets/resolve/main/hf-logo.svg" alt="Hugging Face logo" height="24"/> <strong>Model inference via Hugging Face Inference API is now enabled.</strong> </div>

Example Use:

python

import requests

API_URL = "https://api-inference.huggingface.co/models/hridyansh22/gemma-3-finetune"
headers = {"Authorization": "Bearer YOUR_HF_TOKEN"}

def query(prompt):
    payload = {
        "inputs": "<start_of_turn>user\n" + prompt + "\n<end_of_turn>\n<start_of_turn>model\n",
        "parameters": {
            "do_sample": False,
            "max_new_tokens": 256,
            "temperature": 0.7
        }
    }
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()

print(query("hello who are you?"))