Instructions to use EpistemeAI/MathCoder-Llama3.1-8B-cot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EpistemeAI/MathCoder-Llama3.1-8B-cot with Transformers:

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

pipe = pipeline("text-generation", model="EpistemeAI/MathCoder-Llama3.1-8B-cot")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EpistemeAI/MathCoder-Llama3.1-8B-cot")
model = AutoModelForCausalLM.from_pretrained("EpistemeAI/MathCoder-Llama3.1-8B-cot", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EpistemeAI/MathCoder-Llama3.1-8B-cot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EpistemeAI/MathCoder-Llama3.1-8B-cot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EpistemeAI/MathCoder-Llama3.1-8B-cot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EpistemeAI/MathCoder-Llama3.1-8B-cot

SGLang

How to use EpistemeAI/MathCoder-Llama3.1-8B-cot 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 "EpistemeAI/MathCoder-Llama3.1-8B-cot" \
    --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": "EpistemeAI/MathCoder-Llama3.1-8B-cot",
		"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 "EpistemeAI/MathCoder-Llama3.1-8B-cot" \
        --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": "EpistemeAI/MathCoder-Llama3.1-8B-cot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use EpistemeAI/MathCoder-Llama3.1-8B-cot with Docker Model Runner:
```
docker model run hf.co/EpistemeAI/MathCoder-Llama3.1-8B-cot
```

MathCoder-Llama3.1-8B-cot

Commit History

Dec 31, 2024

06:45
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
bcd9293

Aug 28, 2024

05:11
Update README.md

legolasyiu

Verified signature
449526a

Aug 17, 2024

15:43
(Trained with Unsloth)

legolasyiu

Verified signature
84d0cca
15:35
Upload README.md with huggingface_hub

legolasyiu

Verified signature
0c7d726
15:35
initial commit

legolasyiu

Verified signature
94c7ae5

Commit History

Dec 31, 2024

Adding `safetensors` variant of this model⁠

Aug 28, 2024

Update README.md

Aug 17, 2024

(Trained with Unsloth)

Upload README.md with huggingface_hub

initial commit