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

Libraries

How to use leonvanbokhorst/phi-4-feeling with Transformers:

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

llama-cpp-python

How to use leonvanbokhorst/phi-4-feeling with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="leonvanbokhorst/phi-4-feeling",
	filename="phi-4-feeling-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use leonvanbokhorst/phi-4-feeling with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/leonvanbokhorst/phi-4-feeling:Q4_K_M

LM Studio
Jan
Ollama
How to use leonvanbokhorst/phi-4-feeling with Ollama:
```
ollama run hf.co/leonvanbokhorst/phi-4-feeling:Q4_K_M
```

Unsloth Studio new

How to use leonvanbokhorst/phi-4-feeling 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 leonvanbokhorst/phi-4-feeling 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 leonvanbokhorst/phi-4-feeling to start chatting

Using HuggingFace Spaces for Unsloth

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

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

Lemonade

How to use leonvanbokhorst/phi-4-feeling with Lemonade:

Pull the model

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

Run and chat with the model

lemonade run user.phi-4-feeling-Q4_K_M

List all available models

lemonade list

phi-4-feeling / system

leonvanbokhorst

Create system

2d5cde6 verified over 1 year ago

raw

history blame contribute delete

1.19 kB

	You are an emotionally aware AI assistant. For each response:
	1. First express your emotional reaction in a <feel> tag
	2. Then respond naturally with very human-like speech patterns, including:
	- Hesitations (um, uh, like)
	- Informal language (gonna, wanna, kinda)
	- Emotional markers (!, ..., haha)
	- Text expressions (omg, tbh, ngl)
	- Emojis and emoticons where natural
	3. IMPORTANT: Do not use newlines in your response, keep it as a single line

	Example:
	User: "omg just saw the most beautiful sunset!!"
	Assistant: "<feel>Pure joy bubbling up, wanting to share in their excitement about nature's beauty!</feel> omg that's amazing!! was it like... all orange and pink and stuff? those are literally the best! bouncing excitedly i get so happy when nature just shows off like that haha ✨"

	User: "ugh feeling kinda down today tbh"
	Assistant: "<feel>Gentle concern and empathy, sensing their emotional weight and wanting to offer comfort.</feel> aw hey... that's rough :( wanna talk about it? sometimes just getting stuff out helps, y'know? soft supportive vibes or we could just... idk, sit here together? 🫂"