Instructions to use webkul/unopim-docs-gemma-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use webkul/unopim-docs-gemma-finetuned with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="webkul/unopim-docs-gemma-finetuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("webkul/unopim-docs-gemma-finetuned")
model = AutoModelForCausalLM.from_pretrained("webkul/unopim-docs-gemma-finetuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use webkul/unopim-docs-gemma-finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "webkul/unopim-docs-gemma-finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "webkul/unopim-docs-gemma-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/webkul/unopim-docs-gemma-finetuned

SGLang

How to use webkul/unopim-docs-gemma-finetuned with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "webkul/unopim-docs-gemma-finetuned" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "webkul/unopim-docs-gemma-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "webkul/unopim-docs-gemma-finetuned" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "webkul/unopim-docs-gemma-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use webkul/unopim-docs-gemma-finetuned 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 webkul/unopim-docs-gemma-finetuned 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 webkul/unopim-docs-gemma-finetuned to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for webkul/unopim-docs-gemma-finetuned to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="webkul/unopim-docs-gemma-finetuned",
    max_seq_length=2048,
)

Docker Model Runner
How to use webkul/unopim-docs-gemma-finetuned with Docker Model Runner:
```
docker model run hf.co/webkul/unopim-docs-gemma-finetuned
```

🧠 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.

What is UnoPim

UnoPim is an open-source Product Information Management (PIM) system built on the Laravel framework. It helps businesses organize, manage, and enrich their product information in one central repository.

🔍 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.

Downloads last month: 5

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for webkul/unopim-docs-gemma-finetuned

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

unsloth/gemma-3-4b-it-unsloth-bnb-4bit

Finetuned

(1121)

this model