Instructions to use answerdotai/llama-7b-orca-math-10k-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use answerdotai/llama-7b-orca-math-10k-full with Transformers:

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

pipe = pipeline("text-generation", model="answerdotai/llama-7b-orca-math-10k-full")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("answerdotai/llama-7b-orca-math-10k-full")
model = AutoModelForCausalLM.from_pretrained("answerdotai/llama-7b-orca-math-10k-full")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use answerdotai/llama-7b-orca-math-10k-full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "answerdotai/llama-7b-orca-math-10k-full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "answerdotai/llama-7b-orca-math-10k-full",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/answerdotai/llama-7b-orca-math-10k-full

SGLang

How to use answerdotai/llama-7b-orca-math-10k-full 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 "answerdotai/llama-7b-orca-math-10k-full" \
    --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": "answerdotai/llama-7b-orca-math-10k-full",
		"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 "answerdotai/llama-7b-orca-math-10k-full" \
        --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": "answerdotai/llama-7b-orca-math-10k-full",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use answerdotai/llama-7b-orca-math-10k-full with Docker Model Runner:
```
docker model run hf.co/answerdotai/llama-7b-orca-math-10k-full
```

No model card

Downloads last month: 9

Space using answerdotai/llama-7b-orca-math-10k-full 1

Collection including answerdotai/llama-7b-orca-math-10k-full

Quantized-FT-Orca-Math

Collection

Models trained during quantization aware fine-tuning experiments using PyTorch's FSDP. • 8 items • Updated Aug 20, 2024 • 8