Instructions to use openaccess-ai-collective/StableLManticore-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openaccess-ai-collective/StableLManticore-7B with Transformers:

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

pipe = pipeline("text-generation", model="openaccess-ai-collective/StableLManticore-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openaccess-ai-collective/StableLManticore-7B")
model = AutoModelForCausalLM.from_pretrained("openaccess-ai-collective/StableLManticore-7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openaccess-ai-collective/StableLManticore-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openaccess-ai-collective/StableLManticore-7B"
# 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/StableLManticore-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openaccess-ai-collective/StableLManticore-7B

SGLang

How to use openaccess-ai-collective/StableLManticore-7B 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/StableLManticore-7B" \
    --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/StableLManticore-7B",
		"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/StableLManticore-7B" \
        --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/StableLManticore-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openaccess-ai-collective/StableLManticore-7B with Docker Model Runner:
```
docker model run hf.co/openaccess-ai-collective/StableLManticore-7B
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

StableLManticore 7B

Yeah, don't use this. It was mostly an experiment if it's even plausible. Unfortunately StableLM has poor support for SFT with the huggingface trainer, so no things like flash attention, etc. Ed result is this is nearly impossible to train efficiently. Yes, it's plausible to try to train this with LoRA, but it's not very usable at all.

WandB: https://wandb.ai/wing-lian/stable-manticore-7b/runs/b1qqzf2s

Downloads last month: 11