Instructions to use fdqerq22ds/MathScale-Mistral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fdqerq22ds/MathScale-Mistral with Transformers:

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

pipe = pipeline("text-generation", model="fdqerq22ds/MathScale-Mistral")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fdqerq22ds/MathScale-Mistral")
model = AutoModelForCausalLM.from_pretrained("fdqerq22ds/MathScale-Mistral")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use fdqerq22ds/MathScale-Mistral with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fdqerq22ds/MathScale-Mistral"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fdqerq22ds/MathScale-Mistral",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fdqerq22ds/MathScale-Mistral

SGLang

How to use fdqerq22ds/MathScale-Mistral 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 "fdqerq22ds/MathScale-Mistral" \
    --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": "fdqerq22ds/MathScale-Mistral",
		"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 "fdqerq22ds/MathScale-Mistral" \
        --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": "fdqerq22ds/MathScale-Mistral",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fdqerq22ds/MathScale-Mistral with Docker Model Runner:
```
docker model run hf.co/fdqerq22ds/MathScale-Mistral
```

Overview

This is a reproduced MathScale-Mistral model by finetuning the Mistral-7B-v0.1 on our reproduced MathScaleQA-2M dataset, following the hyperparameters in their original paper to ensure the effectiveness of our reproduction.

Reproduction Details

Fortunately, the reproduction was smooth, and we managed to match the reported performance metrics when evaluating on their MWPBench. Below, we present a comparison between the performance of their official model and our reproduced model:

Model	GSM8K	MATH	CollegeMath	TAL	Math23k	Ape210k	GaokaoBench-Math	AGIE-Gaokao-Math	AGIE-SAT-Math	AGIE-MATH	MicroAverage	MacroAverage
Official MathScale-Mistral	74.8	35.2	21.8	39.9	64.4	46.0	21.4	14.3	57.8	32.9	38.7	40.8
Reproduced MathScale-Mistral	74.0	34.5	22.0	39.6	61.7	45.1	21.6	15.5	56.8	34.4	38.3	40.5

Downloads last month: 9

Safetensors

Model size

7B params

Tensor type

BF16

Dataset used to train fdqerq22ds/MathScale-Mistral

Paper for fdqerq22ds/MathScale-Mistral

MathScale: Scaling Instruction Tuning for Mathematical Reasoning

Paper • 2403.02884 • Published Mar 5, 2024 • 17