metadata

base_model: unsloth/gemma-3-4b-it-unsloth-bnb-4bit
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - gemma3
license: apache-2.0
language:
  - en

🧠 Gemma 3 (4B) Fine-Tuned on UnoPIM Docs — by Webkul

This is a fine-tuned version of unsloth/gemma-3-4b-it-unsloth-bnb-4bit, optimized and accelerated with Unsloth and Hugging Face's TRL for instruction-based text generation tasks.

🔍 Model Summary

Base Model: unsloth/gemma-3-4b-it-unsloth-bnb-4bit
Fine-Tuned By: Webkul
License: Apache-2.0
Language: English
Model Type: Instruction-tuned (4-bit quantized)
Training Boost: ~2x faster training with Unsloth optimizations

📚 Fine-Tuning Dataset

This model has been fine-tuned specifically on official UnoPIM documentation and user guides available at:

👉 https://docs.unopim.com/

Content Covered:

Product Information Management (PIM) workflows
Admin dashboard and module configurations
API usage and endpoints
User roles and access control
Product import/export and sync logic
Custom field and attribute setups
Troubleshooting and common use cases

💡 Use Cases

This model is designed for:

🧾 Q&A on UnoPIM documentation
💬 Chatbots for UnoPIM technical support
🧠 Contextual assistants inside dev tools
🛠️ Knowledge base automation for onboarding users

🚀 Quick Start

You can run this model with Hugging Face’s transformers library:

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "webkul/gemma-3-4b-it-unopim-docs"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

prompt = "How can I import products in bulk using UnoPIM?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=300)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

📄 License This model is distributed under the Apache 2.0 License. See LICENSE for more information.