Instructions to use igor273/phi-4-genaiscript with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use igor273/phi-4-genaiscript with Transformers:

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

pipe = pipeline("text-generation", model="igor273/phi-4-genaiscript")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("igor273/phi-4-genaiscript")
model = AutoModelForCausalLM.from_pretrained("igor273/phi-4-genaiscript")
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]:]))

llama-cpp-python

How to use igor273/phi-4-genaiscript with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="igor273/phi-4-genaiscript",
	filename="unsloth.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use igor273/phi-4-genaiscript with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf igor273/phi-4-genaiscript:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf igor273/phi-4-genaiscript:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf igor273/phi-4-genaiscript:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf igor273/phi-4-genaiscript:Q4_K_M

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 igor273/phi-4-genaiscript:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf igor273/phi-4-genaiscript:Q4_K_M

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 igor273/phi-4-genaiscript:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf igor273/phi-4-genaiscript:Q4_K_M

Use Docker

docker model run hf.co/igor273/phi-4-genaiscript:Q4_K_M

LM Studio
Jan

vLLM

How to use igor273/phi-4-genaiscript with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "igor273/phi-4-genaiscript"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "igor273/phi-4-genaiscript",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/igor273/phi-4-genaiscript:Q4_K_M

SGLang

How to use igor273/phi-4-genaiscript 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 "igor273/phi-4-genaiscript" \
    --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": "igor273/phi-4-genaiscript",
		"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 "igor273/phi-4-genaiscript" \
        --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": "igor273/phi-4-genaiscript",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use igor273/phi-4-genaiscript with Ollama:
```
ollama run hf.co/igor273/phi-4-genaiscript:Q4_K_M
```

Unsloth Studio new

How to use igor273/phi-4-genaiscript 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 igor273/phi-4-genaiscript 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 igor273/phi-4-genaiscript to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for igor273/phi-4-genaiscript to start chatting

Docker Model Runner
How to use igor273/phi-4-genaiscript with Docker Model Runner:
```
docker model run hf.co/igor273/phi-4-genaiscript:Q4_K_M
```

Lemonade

How to use igor273/phi-4-genaiscript with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull igor273/phi-4-genaiscript:Q4_K_M

Run and chat with the model

lemonade run user.phi-4-genaiscript-Q4_K_M

List all available models

lemonade list

Fine-tuned `phi-4` on GenAIScript

This model is a fine-tuned version of microsoft/phi-4 on the GenAIScript training dataset. The base phi-4 model has no prior knowledge of the GenAIScript scripting language, as it was not part of its pretraining data. This fine-tuned version has been specifically trained to understand and generate valid GenAIScript code.

Model Description

Base model: microsoft/phi-4
Fine-tuned on: igor273/genaiscript_training_dataset
Task: Code generation and completion for GenAIScript
Quantized: Yes — optimized for local inference on resource-constrained machines

Dataset

The dataset was created from official Microsoft GenAIScript documentation and real-world code snippets. It includes:

Script generation examples
Function usage and syntax patterns
Control structures and logic flows
Valid use cases and best practices

Capabilities

Fully understands GenAIScript syntax and semantics
Can generate end-to-end scripts from natural language prompts
Can assist in learning and exploring GenAIScript capabilities

Limitations

May require updates if the GenAIScript specification evolves
Quantization may reduce generation precision in some edge cases

License

The base model phi-4 and the dataset are subject to their respective licenses. This fine-tuned version inherits those terms.

Maintained by @igor273

Downloads last month: 34

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for igor273/phi-4-genaiscript

Base model

microsoft/phi-4

Quantized

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

Quantized

(86)

this model

Quantizations

1 model

Fine-tuned phi-4 on GenAIScript