Instructions to use ayman3000/MetaMath-Mistral-7B-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ayman3000/MetaMath-Mistral-7B-quantized with Transformers:

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

pipe = pipeline("text-generation", model="ayman3000/MetaMath-Mistral-7B-quantized")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ayman3000/MetaMath-Mistral-7B-quantized")
model = AutoModelForMultimodalLM.from_pretrained("ayman3000/MetaMath-Mistral-7B-quantized")

llama-cpp-python

How to use ayman3000/MetaMath-Mistral-7B-quantized with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ayman3000/MetaMath-Mistral-7B-quantized",
	filename="metamath-mistral-7b.q4_k_m.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ayman3000/MetaMath-Mistral-7B-quantized with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ayman3000/MetaMath-Mistral-7B-quantized:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ayman3000/MetaMath-Mistral-7B-quantized:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ayman3000/MetaMath-Mistral-7B-quantized:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ayman3000/MetaMath-Mistral-7B-quantized: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 ayman3000/MetaMath-Mistral-7B-quantized:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ayman3000/MetaMath-Mistral-7B-quantized: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 ayman3000/MetaMath-Mistral-7B-quantized:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ayman3000/MetaMath-Mistral-7B-quantized:Q4_K_M

Use Docker

docker model run hf.co/ayman3000/MetaMath-Mistral-7B-quantized:Q4_K_M

LM Studio
Jan

vLLM

How to use ayman3000/MetaMath-Mistral-7B-quantized with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ayman3000/MetaMath-Mistral-7B-quantized"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ayman3000/MetaMath-Mistral-7B-quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ayman3000/MetaMath-Mistral-7B-quantized:Q4_K_M

SGLang

How to use ayman3000/MetaMath-Mistral-7B-quantized 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 "ayman3000/MetaMath-Mistral-7B-quantized" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ayman3000/MetaMath-Mistral-7B-quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ayman3000/MetaMath-Mistral-7B-quantized" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ayman3000/MetaMath-Mistral-7B-quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use ayman3000/MetaMath-Mistral-7B-quantized with Ollama:
```
ollama run hf.co/ayman3000/MetaMath-Mistral-7B-quantized:Q4_K_M
```

Unsloth Studio

How to use ayman3000/MetaMath-Mistral-7B-quantized 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 ayman3000/MetaMath-Mistral-7B-quantized 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 ayman3000/MetaMath-Mistral-7B-quantized to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ayman3000/MetaMath-Mistral-7B-quantized to start chatting

Atomic Chat new
Docker Model Runner
How to use ayman3000/MetaMath-Mistral-7B-quantized with Docker Model Runner:
```
docker model run hf.co/ayman3000/MetaMath-Mistral-7B-quantized:Q4_K_M
```

Lemonade

How to use ayman3000/MetaMath-Mistral-7B-quantized with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ayman3000/MetaMath-Mistral-7B-quantized:Q4_K_M

Run and chat with the model

lemonade run user.MetaMath-Mistral-7B-quantized-Q4_K_M

List all available models

lemonade list

MetaMath-Mistral-7B-quantized

File size: 1,158 Bytes

1ccfb38

{
    "_name_or_path": "ayman3000/MetaMath-Mistral-7B-quantized",
    "architectures": [
        "MistralForCausalLM"
    ],
    "bos_token_id": 1,
    "eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 32768,
    "model_type": "mistral",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-05,
    "rope_theta": 10000.0,
    "sliding_window": 4096,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.35.0.dev0",
    "use_cache": false,
    "vocab_size": 32001,
    "quantization": {
        "enabled": true,
        "methods": ["dynamic", "static"],
        "precision": ["int8"],
        "details": {
            "weights_precision": "int8",
            "activations_precision": "int8",
            "algorithm": "linear_quantization"
        }
    },
    "original_model_repository": "https://huggingface.co/mistralai/Mistral-7B-v0.1",
    "quantized_model_repository": "https://huggingface.co/ayman3000/MetaMath-Mistral-7B-quantized"
}