Instructions to use QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF",
	filename="Llama3.2-3B-ShiningValiant2.Q2_K.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 QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF: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 QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF: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 QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M

Ollama
How to use QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF 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 QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF 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 QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF to start chatting

Pi new

How to use QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M

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": "QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M

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 QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama3.2-3B-ShiningValiant2-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF

This is quantized version of ValiantLabs/Llama3.2-3B-ShiningValiant2 created using llama.cpp

Original Model Card

Shining Valiant 2 is a chat model built on Llama 3.2 3b, finetuned on our data for friendship, insight, knowledge and enthusiasm.

Finetuned on meta-llama/Llama-3.2-3B-Instruct for best available general performance
Trained on a variety of high quality data; focused on science, engineering, technical knowledge, and structured reasoning

Shining Valiant 2 is also available for Llama 3.1 8b.

Version

This is the 2024-09-27 release of Shining Valiant 2 for Llama 3.2 3b.

We've improved and open-sourced our new baseline science-instruct dataset. This release features improvements in physics, chemistry, biology, and computer science.

Future upgrades will continue to expand Shining Valiant's technical knowledge base.

Help us and recommend Shining Valiant 2 to your friends!

Prompting Guide

Shining Valiant 2 uses the Llama 3.2 Instruct prompt format. The example script below can be used as a starting point for general chat:

import transformers
import torch

model_id = "ValiantLabs/Llama3.2-3B-ShiningValiant2"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are an AI assistant."},
    {"role": "user", "content": "Describe the use of chiral auxiliaries in organic synthesis."}
]

outputs = pipeline(
    messages,
    max_new_tokens=2048,
)

print(outputs[0]["generated_text"][-1])

The Model

Shining Valiant 2 is built on top of Llama 3.2 3b Instruct.

The current version of Shining Valiant 2 is trained on technical knowledge using sequelbox/Celestia and general chat capability using sequelbox/Supernova.

Our private data adds specialist knowledge and Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn! Magical. (As a general note: we're hoping to replace and open-source this part of Shining Valiant's dataset with synthetic data soon!)

Shining Valiant 2 is created by Valiant Labs.

Check out our HuggingFace page for our open-source Build Tools models, including the newest version of code-specialist Enigma!

We care about open source. For everyone to use.

We encourage others to finetune further from our models.

Downloads last month: 185

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF

Base model

meta-llama/Llama-3.2-3B-Instruct

Quantized

(455)

this model

Datasets used to train QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF

Evaluation results

acc on Winogrande (5-shot)
self-reported

69.850
normalized accuracy on ARC Challenge (25-Shot)
self-reported

46.250
acc on MMLU College Biology (5-shot)
self-reported

56.250
acc on MMLU High School Biology (5-shot)
self-reported

63.550
acc on MMLU College Chemistry (5-shot)
self-reported

41.000
acc on MMLU High School Chemistry (5-shot)
self-reported

41.380
acc on MMLU College Physics (5-shot)
self-reported

34.310
acc on MMLU High School Physics (5-shot)
self-reported

35.760
acc on MMLU College Computer Science (5-shot)
self-reported

48.000
acc on MMLU High School Computer Science (5-shot)
self-reported

58.000
acc on MMLU STEM (5-shot)
self-reported

45.540
strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

48.900
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

19.110
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

9.140
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

3.020
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

5.490