Instructions to use bveiseh/phi4-magpie-reasoning-v4-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bveiseh/phi4-magpie-reasoning-v4-gguf with Transformers:

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

pipe = pipeline("text-generation", model="bveiseh/phi4-magpie-reasoning-v4-gguf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bveiseh/phi4-magpie-reasoning-v4-gguf", device_map="auto")

PEFT
How to use bveiseh/phi4-magpie-reasoning-v4-gguf with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bveiseh/phi4-magpie-reasoning-v4-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bveiseh/phi4-magpie-reasoning-v4-gguf
# Run inference directly in the terminal:
llama cli -hf bveiseh/phi4-magpie-reasoning-v4-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bveiseh/phi4-magpie-reasoning-v4-gguf
# Run inference directly in the terminal:
llama cli -hf bveiseh/phi4-magpie-reasoning-v4-gguf

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 bveiseh/phi4-magpie-reasoning-v4-gguf
# Run inference directly in the terminal:
./llama-cli -hf bveiseh/phi4-magpie-reasoning-v4-gguf

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 bveiseh/phi4-magpie-reasoning-v4-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bveiseh/phi4-magpie-reasoning-v4-gguf

Use Docker

docker model run hf.co/bveiseh/phi4-magpie-reasoning-v4-gguf

LM Studio
Jan

vLLM

How to use bveiseh/phi4-magpie-reasoning-v4-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bveiseh/phi4-magpie-reasoning-v4-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bveiseh/phi4-magpie-reasoning-v4-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bveiseh/phi4-magpie-reasoning-v4-gguf

SGLang

How to use bveiseh/phi4-magpie-reasoning-v4-gguf 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 "bveiseh/phi4-magpie-reasoning-v4-gguf" \
    --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": "bveiseh/phi4-magpie-reasoning-v4-gguf",
		"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 "bveiseh/phi4-magpie-reasoning-v4-gguf" \
        --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": "bveiseh/phi4-magpie-reasoning-v4-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use bveiseh/phi4-magpie-reasoning-v4-gguf with Ollama:
```
ollama run hf.co/bveiseh/phi4-magpie-reasoning-v4-gguf
```

Unsloth Studio

How to use bveiseh/phi4-magpie-reasoning-v4-gguf 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 bveiseh/phi4-magpie-reasoning-v4-gguf 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 bveiseh/phi4-magpie-reasoning-v4-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bveiseh/phi4-magpie-reasoning-v4-gguf to start chatting

Docker Model Runner
How to use bveiseh/phi4-magpie-reasoning-v4-gguf with Docker Model Runner:
```
docker model run hf.co/bveiseh/phi4-magpie-reasoning-v4-gguf
```

Lemonade

How to use bveiseh/phi4-magpie-reasoning-v4-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bveiseh/phi4-magpie-reasoning-v4-gguf

Run and chat with the model

lemonade run user.phi4-magpie-reasoning-v4-gguf-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

phi4-magpie-reasoning-v4-gguf / README.md

bveiseh

Update README.md

6f95f52 verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

1.78 kB

	---
	license: mit
	datasets:
	- Magpie-Align/Magpie-Reasoning-V2-250K-CoT-Deepseek-R1-Llama-70B
	base_model:
	- microsoft/phi-4
	pipeline_tag: text-generation
	library_name: transformers
	tags:
	- transformers
	- peft
	- bitsandbytes
	- torch
	- accelerate
	- trl
	- LoRA
	---


	# Phi-4 Magpie Reasoning GGUF v4

	This is a GGUF format version of the Phi-4 model fine-tuned on the Magpie dataset (v4).

	## Model Details

	- Base Model: Microsoft Phi-4 (14B parameters)
	- Available Formats:
	- GGUF FP16 (full precision)
	- GGUF Q8 (8-bit quantization)
	- Fine-tuning: LoRA with merged weights
	- Training Dataset: Magpie Reasoning Dataset
	- Version: 4

	## Training Data
	- 2,200 excellent quality examples
	- 3,000 good quality examples
	- Total training samples: 5,200

	## Evaluation Dataset
	- 5 very hard + excellent quality examples
	- 5 medium + excellent quality examples
	- 5 very easy + excellent quality examples

	## Technical Details
	- LoRA Parameters:
	- Rank (r): 24
	- Alpha: 48
	- Target Modules: q_proj, k_proj, v_proj, o_proj
	- Dropout: 0.05

	- Training Configuration:
	- Epochs: 5
	- Learning Rate: 3e-5
	- Batch Size: 1 with gradient accumulation steps of 16
	- Optimizer: AdamW (Fused)
	- Precision: BFloat16 during training
	- Available Formats: FP16 and 8-bit quantized GGUF

	## Usage with llama.cpp

	For CPU inference with the Q8 model:

	main -m phi4-magpie-reasoning-q8.gguf -n 512 --repeat_penalty 1.1 --color -i -r User:

	For GPU inference with the FP16 model:

	main -m phi4-magpie-reasoning-fp16.gguf -n 512 --repeat_penalty 1.1 --color -i -r User: --n-gpu-layers 35

	## Model Sizes
	- GGUF FP16 Format: ~28GB
	- GGUF Q8 Format: ~14GB
	- Original Model (14B parameters)

	## License
	This model inherits the license terms from Microsoft Phi-4 and the Magpie dataset.