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
```

stablelm-3b-4e1t

Commit History

Adding Evaluation Results (#12)

fa4a6a9
verified

jon-tow

leaderboard-pr-bot commited on Mar 7, 2024

fix(README): remove `trust_remote_code` usage after `transformers==4.38.0` support

77fd07d
verified

jon-tow commited on Feb 21, 2024

merge: upload transformers implementation (#10)

0d7bbd4
verified

jon-tow commited on Feb 21, 2024

update(README): lift gate

9449c7d
verified

jon-tow commited on Feb 8, 2024

fix(modeling): use correct `base_model_prefix` name

e3be657
verified

jon-tow commited on Jan 29, 2024

feat: add dropout support

b6e4fc1

jon-tow commited on Jan 23, 2024

fix: make `flash_attn` optional (`trust_remote_code` breaks dynamic module check)

c24bc36

jon-tow commited on Jan 8, 2024

feat: add flash attention v2 (#9)

556500a

jon-tow commited on Jan 5, 2024

fix: remove `StableLMEpochForCausalLM.transformer` refs

c6554ba

jon-tow commited on Oct 25, 2023

fix: rename incorrect access to model

5951257

jon-tow commited on Oct 3, 2023

fix: init proper term

a4750ac

jon-tow commited on Sep 30, 2023

Upload folder using huggingface_hub

846682b

Jonathan Tow commited on Sep 29, 2023

initial commit

88ff7b1

jon-tow commited on Sep 29, 2023

Commit History

Adding Evaluation Results (#12) fa4a6a9 verified

fix(README): remove `trust_remote_code` usage after `transformers==4.38.0` support 77fd07d verified

merge: upload transformers implementation (#10) 0d7bbd4 verified

update(README): lift gate 9449c7d verified

fix(modeling): use correct `base_model_prefix` name e3be657 verified

feat: add dropout support b6e4fc1

fix: make `flash_attn` optional (`trust_remote_code` breaks dynamic module check) c24bc36

feat: add flash attention v2 (#9) 556500a

fix: remove `StableLMEpochForCausalLM.transformer` refs c6554ba

fix: rename incorrect access to model 5951257

fix: init proper term a4750ac

Upload folder using huggingface_hub 846682b

initial commit 88ff7b1