Instructions to use stabilityai/stablelm-3b-4e1t with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stabilityai/stablelm-3b-4e1t with Transformers:

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

pipe = pipeline("text-generation", model="stabilityai/stablelm-3b-4e1t")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-3b-4e1t")
model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-3b-4e1t")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use stabilityai/stablelm-3b-4e1t with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stabilityai/stablelm-3b-4e1t"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stabilityai/stablelm-3b-4e1t",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/stabilityai/stablelm-3b-4e1t

SGLang

How to use stabilityai/stablelm-3b-4e1t 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 "stabilityai/stablelm-3b-4e1t" \
    --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": "stabilityai/stablelm-3b-4e1t",
		"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 "stabilityai/stablelm-3b-4e1t" \
        --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": "stabilityai/stablelm-3b-4e1t",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use stabilityai/stablelm-3b-4e1t with Docker Model Runner:
```
docker model run hf.co/stabilityai/stablelm-3b-4e1t
```

Great Results Finetuning this model for RAG-instruct

by doberst - opened Nov 5, 2023

Discussion

doberst

Nov 5, 2023

Hi StabilityAI team - just wanted to commend you on a great model. We fine-tuned it recently for a RAG-Instruction use case, with excellent results - in fact, it has over-performed many of the 7B models that we have fine-tuned with this objective. Check out the link and the results - https://huggingface.co/llmware/bling-stable-lm-3b-4e1t-v0 - which is part of our BLING model instruct / Q&A fine-tuning on small model series. Thanks for the AWESOME work - and would welcome the chance to connect and collaborate in the future!

Tonic

Nov 10, 2023

well, i came here to say the same thing, i tried it here, cost nothing to train it on a T4, didnt even bother for one whole epoch, and i'm very impressed with the results for something that runs on a cpu upgrade , interesting for such a release, much better than stablecode in my opinion, but please dont stop working in this directionn, it's great 🚀

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