Instructions to use shadicopty/llama3.2-entity with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shadicopty/llama3.2-entity with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="shadicopty/llama3.2-entity",
	filename="unsloth.F16.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 shadicopty/llama3.2-entity with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf shadicopty/llama3.2-entity:F16
# Run inference directly in the terminal:
llama-cli -hf shadicopty/llama3.2-entity:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf shadicopty/llama3.2-entity:F16
# Run inference directly in the terminal:
llama-cli -hf shadicopty/llama3.2-entity:F16

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 shadicopty/llama3.2-entity:F16
# Run inference directly in the terminal:
./llama-cli -hf shadicopty/llama3.2-entity:F16

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 shadicopty/llama3.2-entity:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf shadicopty/llama3.2-entity:F16

Use Docker

docker model run hf.co/shadicopty/llama3.2-entity:F16

LM Studio
Jan
Ollama
How to use shadicopty/llama3.2-entity with Ollama:
```
ollama run hf.co/shadicopty/llama3.2-entity:F16
```

Unsloth Studio new

How to use shadicopty/llama3.2-entity 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 shadicopty/llama3.2-entity 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 shadicopty/llama3.2-entity to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for shadicopty/llama3.2-entity to start chatting

Pi new

How to use shadicopty/llama3.2-entity with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf shadicopty/llama3.2-entity:F16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "llama3.2-entity"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use shadicopty/llama3.2-entity with Docker Model Runner:
```
docker model run hf.co/shadicopty/llama3.2-entity:F16
```

Lemonade

How to use shadicopty/llama3.2-entity with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull shadicopty/llama3.2-entity:F16

Run and chat with the model

lemonade run user.llama3.2-entity-F16

List all available models

lemonade list

This model is fine tuned from Llama3.2-3b, it is trained to extract names of companies, projects and people in a specific json format.

The intent is to use this on desktop to anonymyze text that later goes on to cloud

The model was trained using unsloth on google collab

Downloads last month: 44

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for shadicopty/llama3.2-entity

Quantizations

1 model