Instructions to use openaccess-ai-collective/manticore-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openaccess-ai-collective/manticore-13b with Transformers:

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

pipe = pipeline("text-generation", model="openaccess-ai-collective/manticore-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openaccess-ai-collective/manticore-13b")
model = AutoModelForCausalLM.from_pretrained("openaccess-ai-collective/manticore-13b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openaccess-ai-collective/manticore-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openaccess-ai-collective/manticore-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openaccess-ai-collective/manticore-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openaccess-ai-collective/manticore-13b

SGLang

How to use openaccess-ai-collective/manticore-13b 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 "openaccess-ai-collective/manticore-13b" \
    --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": "openaccess-ai-collective/manticore-13b",
		"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 "openaccess-ai-collective/manticore-13b" \
        --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": "openaccess-ai-collective/manticore-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openaccess-ai-collective/manticore-13b with Docker Model Runner:
```
docker model run hf.co/openaccess-ai-collective/manticore-13b
```

specific instruct prompt to use

by digitous - opened May 19, 2023

Discussion

digitous

May 19, 2023

Alpaca is well known to use

Instruction:

Response:

And a lot of people say, with WizardLM and Vicuna it's
Human:
Assistant:

However, looking at WizardLM's own training data they link to from their Git, it's
human:
gpt:

Can you help show the specific instruct prompt that works with Manticore and Mega?
Thank you for your AWESOME work!

tangles

May 19, 2023

•

edited May 19, 2023

Check the model card. Same as llama:

### Instruction: <prompt>
### Assistant:

winglian

Open Access AI Collective org May 19, 2023

Manticore gets fed several different prompts, so it's pretty good at figuring out whichever one you use.

digitous

May 19, 2023

Ah very cool. I was curious if several instruct types blended together would yield a model that has an intrinsic understanding of a generalized instruct format. Thank you for your hard work!

winglian changed discussion status to closed May 19, 2023

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