Instructions to use Navpy/phi-3.5-AI-Vtuber-json with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Navpy/phi-3.5-AI-Vtuber-json with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Navpy/phi-3.5-AI-Vtuber-json",
	filename="v1-phi-3.5-mini-instruct.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 Navpy/phi-3.5-AI-Vtuber-json with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Navpy/phi-3.5-AI-Vtuber-json:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Navpy/phi-3.5-AI-Vtuber-json:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Navpy/phi-3.5-AI-Vtuber-json:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Navpy/phi-3.5-AI-Vtuber-json: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 Navpy/phi-3.5-AI-Vtuber-json:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Navpy/phi-3.5-AI-Vtuber-json: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 Navpy/phi-3.5-AI-Vtuber-json:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Navpy/phi-3.5-AI-Vtuber-json:Q4_K_M

Use Docker

docker model run hf.co/Navpy/phi-3.5-AI-Vtuber-json:Q4_K_M

LM Studio
Jan

vLLM

How to use Navpy/phi-3.5-AI-Vtuber-json with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Navpy/phi-3.5-AI-Vtuber-json"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Navpy/phi-3.5-AI-Vtuber-json",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Navpy/phi-3.5-AI-Vtuber-json:Q4_K_M

Ollama
How to use Navpy/phi-3.5-AI-Vtuber-json with Ollama:
```
ollama run hf.co/Navpy/phi-3.5-AI-Vtuber-json:Q4_K_M
```

Unsloth Studio new

How to use Navpy/phi-3.5-AI-Vtuber-json 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 Navpy/phi-3.5-AI-Vtuber-json 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 Navpy/phi-3.5-AI-Vtuber-json to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Navpy/phi-3.5-AI-Vtuber-json to start chatting

Docker Model Runner
How to use Navpy/phi-3.5-AI-Vtuber-json with Docker Model Runner:
```
docker model run hf.co/Navpy/phi-3.5-AI-Vtuber-json:Q4_K_M
```

Lemonade

How to use Navpy/phi-3.5-AI-Vtuber-json with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Navpy/phi-3.5-AI-Vtuber-json:Q4_K_M

Run and chat with the model

lemonade run user.phi-3.5-AI-Vtuber-json-Q4_K_M

List all available models

lemonade list

📦 Model Versions

This repository contains two versions of Nova. Choose the one that fits your needs:

Version	File	Personality	JSON Behavior
V1 (Original)	`v1-phi-3.5-mini-instruct.Q4_K_M.gguf`	Balanced, less talkative, stable	Requires system prompt (see below)
V2 (Latest)	`v2-phi-3.5-mini-instruct.Q4_K_M.gguf`	More talkative, emotional, expressive	Native JSON — no prompt needed (But still Prompt recommended for less hallucinations)

🔑 V1 System Prompt (Required)

For V1 only — you must use the ModelFile provided to get the best results out of the model.

(Change the file name in the Modelfile to the one you downloaded)

✨ V2 (Native JSON)

V2 was trained for 2 epochs (0.62 loss) to make JSON its native language. It works with or without a system prompt, and is more talkative and emotionally expressive by default.

Recommendation: Use the provided Modelfile for best results with Ollama.

(Change the file name in the Modelfile to the one you downloaded)

📥 Download

V1: v1-phi-3.5-mini-instruct.Q4_K_M.gguf
V2: v2-phi-3.5-mini-instruct.Q4_K_M.gguf

Both files are visible in the Files tab above.

💡 Which one should I use?

Choose V1 if: You want the original, balanced smart Nova and less talkative.
Choose V2 if: You want a more talkative, emotional Nova.

Version 2.0: The "Native JSON" Update

The model has been completely re-trained from the ground up to be more stable, expressive, and structurally sound.

What's New in V2?

While V1 was successfully fine-tuned to repond in JSON format, it required a System Prompt to guide the model for that behavior. V2 has been deeply trained 2epochs (0.62 loss) to make JSON and the personality its native language. It now understands the JSON structure at a foundational level, making it more 'alive,' talkative, and responsive even with minimal prompting. If you are downloading the new version, you can still use your old Modelfile! However, you will notice that responses feels much more talkative and emotional because the model is deeply fine-tuned.

For Ollama users A Modelfile is added for you to get the best results out of the model(RECOMMENDED).

Disclaimer

Modelfile is only for guiding the LLM to always respond in structured way without rambling or generating tokens endlessly, the structure of response and personality is all came from true fine-tuning.

phi-3.5-AI-Vtuber-json : GGUF

This is a fine-tuned large language model based on Phi-3.5 Mini-Instruct, optimized for AI companion applications that require strict, machine-readable JSON output.

This was trained to always return responses in a consistent JSON format with response and emotion fields. This makes it easy to integrate with software that parses and uses AI outputs programmatically.

🔗 Project Nova, where i have used this model: https://github.com/Navjot-Singh7/Project-Nova

Model Overview

Base Model: Phi-3.5 Mini-Instruct
Fine-Tuned For: AI companion behavior with structured JSON output Output Format:

{
  "response": "...",
  "emotion": "..."
}

Primary Use Case: AI companion systems and applications where responses must be machine-readable.

Capabilities

This model has been fine-tuned to:
- Generate companion-style text that is appropriate, engaging, and in JSON format.
- Always include both:
  - response: the AI’s text output
  - emotion: a tag describing the emotional tone of the response

Produce outputs that are consistent and reliable for code integration.

Intended Use

Primary Use Cases

AI companion applications
Virtual characters or avatars
VTuber or assistant personalities -Applications that require structured LLM output
Emotion-aware conversational systems

Training Details

Custom Dataset - I created my own labeled dataset with 10–20 original samples with JSON-style examples.

Synthetic Data Generation - Then I expanded this initial dataset using another language model to create a synthetic training corpus of ~1,800 samples.

Fine-Tuning Environment - Training was performed using Google Colab.

Dataset Composition - The dataset contains structured examples that guide the model to generate JSON output with response and emotion.

Usage Example

Below is an example of how the model might respond in your application:

{
  "response": "Hello! I'm fine thank you... uhm.. did you have a good day?", 
  "emotion": "happy"
}

This makes it easy to parse and handle both the semantic content (response) and the emotional context (emotion) in code.

License

This model is licensed under the MIT License. You are free to use, modify, and distribute this model for personal or educational purposes.

Available Model files:

phi-3.5-mini-instruct.Q4_K_M.gguf

Ollama

An Ollama Modelfile is included for easy deployment. This was trained 2x faster with Unsloth

Downloads last month: 299

GGUF

Model size

4B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for Navpy/phi-3.5-AI-Vtuber-json

Base model

microsoft/Phi-3.5-mini-instruct

Quantized

(183)

this model