Instructions to use scottfrasso/scheduler-llama-3.1-8b-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use scottfrasso/scheduler-llama-3.1-8b-sft with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="scottfrasso/scheduler-llama-3.1-8b-sft",
	filename="model.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use scottfrasso/scheduler-llama-3.1-8b-sft with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf scottfrasso/scheduler-llama-3.1-8b-sft
# Run inference directly in the terminal:
llama-cli -hf scottfrasso/scheduler-llama-3.1-8b-sft

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf scottfrasso/scheduler-llama-3.1-8b-sft
# Run inference directly in the terminal:
llama-cli -hf scottfrasso/scheduler-llama-3.1-8b-sft

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 scottfrasso/scheduler-llama-3.1-8b-sft
# Run inference directly in the terminal:
./llama-cli -hf scottfrasso/scheduler-llama-3.1-8b-sft

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 scottfrasso/scheduler-llama-3.1-8b-sft
# Run inference directly in the terminal:
./build/bin/llama-cli -hf scottfrasso/scheduler-llama-3.1-8b-sft

Use Docker

docker model run hf.co/scottfrasso/scheduler-llama-3.1-8b-sft

LM Studio
Jan
Ollama
How to use scottfrasso/scheduler-llama-3.1-8b-sft with Ollama:
```
ollama run hf.co/scottfrasso/scheduler-llama-3.1-8b-sft
```

Unsloth Studio

How to use scottfrasso/scheduler-llama-3.1-8b-sft 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 scottfrasso/scheduler-llama-3.1-8b-sft 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 scottfrasso/scheduler-llama-3.1-8b-sft to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for scottfrasso/scheduler-llama-3.1-8b-sft to start chatting

How to use scottfrasso/scheduler-llama-3.1-8b-sft with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf scottfrasso/scheduler-llama-3.1-8b-sft

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": "scottfrasso/scheduler-llama-3.1-8b-sft"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use scottfrasso/scheduler-llama-3.1-8b-sft with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf scottfrasso/scheduler-llama-3.1-8b-sft

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default scottfrasso/scheduler-llama-3.1-8b-sft

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use scottfrasso/scheduler-llama-3.1-8b-sft with Docker Model Runner:
```
docker model run hf.co/scottfrasso/scheduler-llama-3.1-8b-sft
```

Lemonade

How to use scottfrasso/scheduler-llama-3.1-8b-sft with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull scottfrasso/scheduler-llama-3.1-8b-sft

Run and chat with the model

lemonade run user.scheduler-llama-3.1-8b-sft-{{QUANT_TAG}}

List all available models

lemonade list

Scheduler Llama 3.1 8B SFT (5-epoch version)

A fine-tuned Llama 3.1 8B Instruct model for meeting scheduling with tool calling support.

Model Details

Base model: meta-llama/Llama-3.1-8B-Instruct
Task: Meeting scheduling assistant with tool calling
Quantization: Q4_K_M GGUF
Training format: Ollama-compatible tool-calling template

Training Details

Method: LoRA SFT (Supervised Fine-Tuning) with 4-bit QLoRA
Training examples: 449
Epochs: 5
LoRA config: r=16, alpha=32
Hardware: A100-40GB
Train loss: 0.080
Eval loss: 0.079

Usage

This model is designed to be used with Ollama. Download the GGUF file and create a Modelfile pointing to it, then run with Ollama.

Downloads last month: 3

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for scottfrasso/scheduler-llama-3.1-8b-sft

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Quantized

(644)

this model