Instructions to use oriolrius/phi3-avro-gguf-q4km with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oriolrius/phi3-avro-gguf-q4km with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="oriolrius/phi3-avro-gguf-q4km",
	filename="model.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use oriolrius/phi3-avro-gguf-q4km with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf oriolrius/phi3-avro-gguf-q4km
# Run inference directly in the terminal:
llama-cli -hf oriolrius/phi3-avro-gguf-q4km

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf oriolrius/phi3-avro-gguf-q4km
# Run inference directly in the terminal:
llama-cli -hf oriolrius/phi3-avro-gguf-q4km

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf oriolrius/phi3-avro-gguf-q4km
# Run inference directly in the terminal:
./llama-cli -hf oriolrius/phi3-avro-gguf-q4km

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf oriolrius/phi3-avro-gguf-q4km
# Run inference directly in the terminal:
./build/bin/llama-cli -hf oriolrius/phi3-avro-gguf-q4km

Use Docker

docker model run hf.co/oriolrius/phi3-avro-gguf-q4km

LM Studio
Jan

vLLM

How to use oriolrius/phi3-avro-gguf-q4km with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oriolrius/phi3-avro-gguf-q4km"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oriolrius/phi3-avro-gguf-q4km",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/oriolrius/phi3-avro-gguf-q4km

Ollama
How to use oriolrius/phi3-avro-gguf-q4km with Ollama:
```
ollama run hf.co/oriolrius/phi3-avro-gguf-q4km
```

Unsloth Studio

How to use oriolrius/phi3-avro-gguf-q4km 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 oriolrius/phi3-avro-gguf-q4km 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 oriolrius/phi3-avro-gguf-q4km to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for oriolrius/phi3-avro-gguf-q4km to start chatting

Atomic Chat new
Docker Model Runner
How to use oriolrius/phi3-avro-gguf-q4km with Docker Model Runner:
```
docker model run hf.co/oriolrius/phi3-avro-gguf-q4km
```

Lemonade

How to use oriolrius/phi3-avro-gguf-q4km with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull oriolrius/phi3-avro-gguf-q4km

Run and chat with the model

lemonade run user.phi3-avro-gguf-q4km-{{QUANT_TAG}}

List all available models

lemonade list

Phi-3 Mini 4K AVRO Fine-tuned Model (Ollama)

This is a fine-tuned version of Microsoft's Phi-3 Mini 4K model, specifically trained on AVRO-related tasks and exported for use with Ollama.

Model Details

Base Model: Microsoft Phi-3 Mini 4K
Fine-tuning: LoRA with rank 32, alpha 64, 20 epochs
Export Format: GGUF (Quantized q4_k_m)
Export Date: 2025-09-15
Export Tool: Docker-based Ollama export
Model Size: ~7.2GB (quantized)

Files

model.gguf: The quantized model file in GGUF format
Modelfile: Ollama configuration file with model parameters
docker-compose.yml: Docker setup for running the model
setup_ollama.sh: Script to set up Ollama with this model
test_model.sh: Script to test the model functionality

Usage

With Ollama

Download the model files

Run the setup script:

chmod +x setup_ollama.sh
./setup_ollama.sh

Use the model:
```
ollama run phi3-avro
```

With Docker Compose

docker-compose up -d

Model Parameters

Temperature: 0.7
Top-p: 0.9
Top-k: 40
Max tokens: 2048

Fine-tuning Details

This model was fine-tuned using LoRA (Low-Rank Adaptation) technique:

Rank: 32
Alpha: 64
Training epochs: 20
Training completed: 2025-09-14

The model has been specifically trained to understand and work with AVRO schemas, data serialization, and related data engineering tasks.

License

This model inherits the license from the base Phi-3 Mini model. Please refer to Microsoft's Phi-3 licensing terms.

Technical Specifications

Quantization: q4_k_m (4-bit quantization with k-means)
Context length: 4096 tokens
Export method: Docker container compilation
Compatible with: Ollama, llama.cpp ecosystem

Downloads last month: 4

GGUF

Model size

4B params

Architecture

phi3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for oriolrius/phi3-avro-gguf-q4km

Base model

microsoft/Phi-3-mini-4k-instruct

Quantized

(166)

this model