Instructions to use GOAT-AI/GOAT-7B-Community with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GOAT-AI/GOAT-7B-Community with Transformers:

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

pipe = pipeline("text-generation", model="GOAT-AI/GOAT-7B-Community")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GOAT-AI/GOAT-7B-Community")
model = AutoModelForCausalLM.from_pretrained("GOAT-AI/GOAT-7B-Community")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use GOAT-AI/GOAT-7B-Community with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/GOAT-AI/GOAT-7B-Community

SGLang

How to use GOAT-AI/GOAT-7B-Community 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 "GOAT-AI/GOAT-7B-Community" \
    --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": "GOAT-AI/GOAT-7B-Community",
		"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 "GOAT-AI/GOAT-7B-Community" \
        --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": "GOAT-AI/GOAT-7B-Community",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GOAT-AI/GOAT-7B-Community with Docker Model Runner:
```
docker model run hf.co/GOAT-AI/GOAT-7B-Community
```

Prompt Format

by MK-CUPIST - opened Aug 11, 2023

Discussion

MK-CUPIST

Aug 11, 2023

Hey I am interested in your amazing model, and wanting to try it out.
To get the most out of the model can you share the intended or trained prompt format please?
Thank you!

myxik

Aug 12, 2023

Hi! Thank you for your interest. Prompt format that we were consistent to was

\n###USER:<user-text>\n###ASSISTANT:<assistant-text>\n

hopefully, that answers your question

MK-CUPIST

Aug 17, 2023

Thank you!

MK-CUPIST changed discussion status to closed Aug 17, 2023

MK-CUPIST changed discussion status to open Aug 17, 2023

MK-CUPIST

Aug 17, 2023

I have one more question. Is there no system prompt for the model?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment