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

Navpy commited on Apr 13

Commit

3f3fac9

verified ·

1 Parent(s): 5526d4e

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -24,6 +24,7 @@ This repository contains **two versions** of Nova. Choose the one that fits your
 ## 🔑 V1 System Prompt (Required)
 For **V1 only** — you must use the ModelFile provided to get the best results out of the model.
 ---
 ## ✨ V2 (Native JSON)
@@ -32,6 +33,8 @@ V2 was trained for 2 epochs (0.62 loss) to make JSON its native language. It wor
 > **Recommendation:** Use the provided `Modelfile` for best results with Ollama.
 ---
 ## 📥 Download

 ## 🔑 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)
 > **Recommendation:** Use the provided `Modelfile` for best results with Ollama.
+> **(Change the file name in the Modelfile to the one you downloaded)**
 ---
 ## 📥 Download