Instructions to use Ishika08/phi-4_fine-tuned_mdl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ishika08/phi-4_fine-tuned_mdl with Transformers:

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

pipe = pipeline("text-generation", model="Ishika08/phi-4_fine-tuned_mdl")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Ishika08/phi-4_fine-tuned_mdl", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ishika08/phi-4_fine-tuned_mdl with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ishika08/phi-4_fine-tuned_mdl"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ishika08/phi-4_fine-tuned_mdl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ishika08/phi-4_fine-tuned_mdl

SGLang

How to use Ishika08/phi-4_fine-tuned_mdl 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 "Ishika08/phi-4_fine-tuned_mdl" \
    --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": "Ishika08/phi-4_fine-tuned_mdl",
		"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 "Ishika08/phi-4_fine-tuned_mdl" \
        --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": "Ishika08/phi-4_fine-tuned_mdl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Ishika08/phi-4_fine-tuned_mdl 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 Ishika08/phi-4_fine-tuned_mdl 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 Ishika08/phi-4_fine-tuned_mdl to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ishika08/phi-4_fine-tuned_mdl to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Ishika08/phi-4_fine-tuned_mdl",
    max_seq_length=2048,
)

Docker Model Runner
How to use Ishika08/phi-4_fine-tuned_mdl with Docker Model Runner:
```
docker model run hf.co/Ishika08/phi-4_fine-tuned_mdl
```

Uploaded model

Developed by: Ishika08
License: apache-2.0
Finetuned from model : unsloth/phi-4-unsloth-bnb-4bit

This phi model was trained 2x faster with Unsloth and Huggingface's TRL library.

How to Use the Model for Inferencing

You can use the model for inferencing via Hugging Face's API by following the steps below:

1. Install Required Libraries

Ensure that you have the requests library installed:

pip install requests

Steps to use the model for inferencing using Hugging Face API

import requests

API URL for the model hosted on Hugging Face

API_URL = "https://api-inference.huggingface.co/models/Ishika08/phi-4_fine-tuned_mdl"

Set up your Hugging Face API token

HEADERS = {"Authorization": f"Bearer token_id"}

The input you want to pass to the model

payload = { "inputs": "What is the capital of France? Tell me some of the tourist places in bullet points." }

Make the request to the API

response = requests.post(API_URL, headers=HEADERS, json=payload)

Print the response from the model

print(response.json()) # Get the response output

OUTPUT

{ "generated_text": "Paris is the capital of France. Some of the famous tourist places include:\n- Eiffel Tower\n- Louvre Museum\n- Notre-Dame Cathedral\n- Sacré-Cœur Basilica" }

Steps to use model using InferenceClient library from huggingface_hub

from huggingface_hub import InferenceClient

Initialize the client with model name and Hugging Face token

client = InferenceClient(model="Ishika08/phi-4_fine-tuned_mdl", token=""")

Perform inference (text generation in this case)

response = client.text_generation("What is the capital of France? Tell me about Eiffel Tower history in bullet points.")

Print the response from the model

print(response)

Downloads last month: 2

Model tree for Ishika08/phi-4_fine-tuned_mdl

Base model

microsoft/phi-4

Quantized

unsloth/phi-4-unsloth-bnb-4bit

Finetuned

(350)

this model