Instructions to use MathGenie/MathGenie-Mixtral-8x7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MathGenie/MathGenie-Mixtral-8x7B with Transformers:

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

pipe = pipeline("text-generation", model="MathGenie/MathGenie-Mixtral-8x7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MathGenie/MathGenie-Mixtral-8x7B")
model = AutoModelForCausalLM.from_pretrained("MathGenie/MathGenie-Mixtral-8x7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MathGenie/MathGenie-Mixtral-8x7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MathGenie/MathGenie-Mixtral-8x7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MathGenie/MathGenie-Mixtral-8x7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MathGenie/MathGenie-Mixtral-8x7B

SGLang

How to use MathGenie/MathGenie-Mixtral-8x7B 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 "MathGenie/MathGenie-Mixtral-8x7B" \
    --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": "MathGenie/MathGenie-Mixtral-8x7B",
		"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 "MathGenie/MathGenie-Mixtral-8x7B" \
        --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": "MathGenie/MathGenie-Mixtral-8x7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MathGenie/MathGenie-Mixtral-8x7B with Docker Model Runner:
```
docker model run hf.co/MathGenie/MathGenie-Mixtral-8x7B
```

MathGenie commited on May 4, 2024

Commit

323fc5f

verified ·

1 Parent(s): 8a067f8

Update README.md

Browse files

Files changed (1) hide show

README.md +17 -0

README.md CHANGED Viewed

@@ -44,6 +44,23 @@ Our [MathGenie-Mixtral-8x7B](https://huggingface.co/MathGenie/MathGenie-Mixtral-
 ### Inference & Evaluation
 Please refer to the [MathCoder repo](https://github.com/mathllm/MathCoder) for the detailed code for inference and evaluation of our MathGenieLM models.
 ## Citation

 ### Inference & Evaluation
+**template**
+```
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>' }}{% elif message['role'] == 'system' %}
+{{ '<|system|>' }}{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>' }}{% endif %}
+{% for block in message['content'] %}
+{% if block['type'] == 'text' %}
+{{ '<|text|>' }}{% elif block['type'] == 'code' %}
+{{ '<|code|>' }}{% elif block['type'] == 'execution' %}
+{{ '<|execution|>' }}{% endif %}
+{{ block['content'] + '<|endofblock|>' }}{% endfor %}
+{{ '<|endofmessage|>' }}{% endfor %}
+```
 Please refer to the [MathCoder repo](https://github.com/mathllm/MathCoder) for the detailed code for inference and evaluation of our MathGenieLM models.
 ## Citation