Instructions to use ColoAI/Colo-Math-mini-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ColoAI/Colo-Math-mini-preview with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "ColoAI/Colo-Math-mini-preview")

Transformers

How to use ColoAI/Colo-Math-mini-preview with Transformers:

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

pipe = pipeline("text-generation", model="ColoAI/Colo-Math-mini-preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ColoAI/Colo-Math-mini-preview", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ColoAI/Colo-Math-mini-preview with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ColoAI/Colo-Math-mini-preview

SGLang

How to use ColoAI/Colo-Math-mini-preview 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 "ColoAI/Colo-Math-mini-preview" \
    --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": "ColoAI/Colo-Math-mini-preview",
		"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 "ColoAI/Colo-Math-mini-preview" \
        --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": "ColoAI/Colo-Math-mini-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ColoAI/Colo-Math-mini-preview with Docker Model Runner:
```
docker model run hf.co/ColoAI/Colo-Math-mini-preview
```

Model Details

Model Description

this model is really good at math and can code to get the math answered.

Developed by: [ColoAI]
Language(s) (NLP): [English]
License: [Apache 2.0 license]
Finetuned from model: [qwen2-7b]

Uses

this model is only used for math! don't use it for anything else!

Out-of-Scope Use

this model cannot, write, chat, or roleplay. only math is used for this model.

PEFT 0.16.0

Downloads last month: 2

Model tree for ColoAI/Colo-Math-mini-preview

Base model

Qwen/Qwen2-7B

Finetuned

Qwen/Qwen2-7B-Instruct

Adapter

(409)

this model