Instructions to use QuantFactory/MAmmoTH2-8B-Plus-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/MAmmoTH2-8B-Plus-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="QuantFactory/MAmmoTH2-8B-Plus-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantFactory/MAmmoTH2-8B-Plus-GGUF", dtype="auto")

llama-cpp-python

How to use QuantFactory/MAmmoTH2-8B-Plus-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/MAmmoTH2-8B-Plus-GGUF",
	filename="MAmmoTH2-8B-Plus.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/MAmmoTH2-8B-Plus-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/MAmmoTH2-8B-Plus-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/MAmmoTH2-8B-Plus-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/MAmmoTH2-8B-Plus-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/MAmmoTH2-8B-Plus-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/MAmmoTH2-8B-Plus-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/MAmmoTH2-8B-Plus-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/MAmmoTH2-8B-Plus-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/MAmmoTH2-8B-Plus-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/MAmmoTH2-8B-Plus-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/MAmmoTH2-8B-Plus-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/MAmmoTH2-8B-Plus-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/MAmmoTH2-8B-Plus-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantFactory/MAmmoTH2-8B-Plus-GGUF:Q4_K_M

SGLang

How to use QuantFactory/MAmmoTH2-8B-Plus-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "QuantFactory/MAmmoTH2-8B-Plus-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/MAmmoTH2-8B-Plus-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "QuantFactory/MAmmoTH2-8B-Plus-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/MAmmoTH2-8B-Plus-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use QuantFactory/MAmmoTH2-8B-Plus-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/MAmmoTH2-8B-Plus-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/MAmmoTH2-8B-Plus-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/MAmmoTH2-8B-Plus-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/MAmmoTH2-8B-Plus-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/MAmmoTH2-8B-Plus-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/MAmmoTH2-8B-Plus-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/MAmmoTH2-8B-Plus-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/MAmmoTH2-8B-Plus-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/MAmmoTH2-8B-Plus-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MAmmoTH2-8B-Plus-GGUF-Q4_K_M

List all available models

lemonade list

🦣 QuantFactory/MAmmoTH2-8B-Plus-GGUF

This is quantized version of TIGER-Lab/MAmmoTH2-8B-Plus created using llama.cpp

Introduction

Project Page: https://tiger-ai-lab.github.io/MAmmoTH2/

Paper: https://arxiv.org/pdf/2405.03548

Code: https://github.com/TIGER-AI-Lab/MAmmoTH2

Introducing 🦣 MAmmoTH2, a game-changer in improving the reasoning abilities of large language models (LLMs) through innovative instruction tuning. By efficiently harvesting 10 million instruction-response pairs from the pre-training web corpus, we've developed MAmmoTH2 models that significantly boost performance on reasoning benchmarks. For instance, MAmmoTH2-7B (Mistral) sees its performance soar from 11% to 36.7% on MATH and from 36% to 68.4% on GSM8K, all without training on any domain-specific data. Further training on public instruction tuning datasets yields MAmmoTH2-Plus, setting new standards in reasoning and chatbot benchmarks. Our work presents a cost-effective approach to acquiring large-scale, high-quality instruction data, offering a fresh perspective on enhancing LLM reasoning abilities.

	Base Model	MAmmoTH2	MAmmoTH2-Plus
7B	Mistral	🦣 MAmmoTH2-7B	🦣 MAmmoTH2-7B-Plus
8B	Llama-3	🦣 MAmmoTH2-8B	🦣 MAmmoTH2-8B-Plus
8x7B	Mixtral	🦣 MAmmoTH2-8x7B	🦣 MAmmoTH2-8x7B-Plus

Training Data

Please refer to https://huggingface.co/datasets/TIGER-Lab/WebInstructSub for more details.

Training Procedure

The models are fine-tuned with the WEBINSTRUCT dataset using the original Llama-3, Mistral and Mistal models as base models. The training procedure varies for different models based on their sizes. Check out our paper for more details.

Evaluation

The models are evaluated using open-ended and multiple-choice math problems from several datasets. Here are the results:

Model	TheoremQA	MATH	GSM8K	GPQA	MMLU-ST	BBH	ARC-C	Avg
MAmmoTH2-7B (Updated)	29.0	36.7	68.4	32.4	62.4	58.6	81.7	52.7
MAmmoTH2-8B (Updated)	30.3	35.8	70.4	35.2	64.2	62.1	82.2	54.3
MAmmoTH2-8x7B	32.2	39.0	75.4	36.8	67.4	71.1	87.5	58.9
MAmmoTH2-7B-Plus (Updated)	31.2	46.0	84.6	33.8	63.8	63.3	84.4	58.1
MAmmoTH2-8B-Plus (Updated)	31.5	43.0	85.2	35.8	66.7	69.7	84.3	59.4
MAmmoTH2-8x7B-Plus	34.1	47.0	86.4	37.8	72.4	74.1	88.4	62.9

To reproduce our results, please refer to https://github.com/TIGER-AI-Lab/MAmmoTH2/tree/main/math_eval.

Usage

You can use the models through Huggingface's Transformers library. Use the pipeline function to create a text-generation pipeline with the model of your choice, then feed in a math problem to get the solution. Check our Github repo for more advanced use: https://github.com/TIGER-AI-Lab/MAmmoTH2

Limitations

We've tried our best to build math generalist models. However, we acknowledge that the models' performance may vary based on the complexity and specifics of the math problem. Still not all mathematical fields can be covered comprehensively.

Downloads last month: 234

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for QuantFactory/MAmmoTH2-8B-Plus-GGUF

Base model

TIGER-Lab/MAmmoTH2-8B-Plus

Quantized

(5)

this model

Dataset used to train QuantFactory/MAmmoTH2-8B-Plus-GGUF

Paper for QuantFactory/MAmmoTH2-8B-Plus-GGUF

MAmmoTH2: Scaling Instructions from the Web

Paper • 2405.03548 • Published May 6, 2024 • 6