Instructions to use stabilityai/japanese-stablelm-instruct-alpha-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stabilityai/japanese-stablelm-instruct-alpha-7b with Transformers:

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

pipe = pipeline("text-generation", model="stabilityai/japanese-stablelm-instruct-alpha-7b", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("stabilityai/japanese-stablelm-instruct-alpha-7b", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use stabilityai/japanese-stablelm-instruct-alpha-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/stabilityai/japanese-stablelm-instruct-alpha-7b

SGLang

How to use stabilityai/japanese-stablelm-instruct-alpha-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 "stabilityai/japanese-stablelm-instruct-alpha-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": "stabilityai/japanese-stablelm-instruct-alpha-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 "stabilityai/japanese-stablelm-instruct-alpha-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": "stabilityai/japanese-stablelm-instruct-alpha-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use stabilityai/japanese-stablelm-instruct-alpha-7b with Docker Model Runner:
```
docker model run hf.co/stabilityai/japanese-stablelm-instruct-alpha-7b
```

Running locally?

by chigaijin - opened Aug 10, 2023

Discussion

chigaijin

Aug 10, 2023

I'm trying to run this locally via oobabooga, but I get an error that it's trying to access a gated repo (here, which I've gained access to). As I have the model downloaded it shouldn't need to access a repo. Is there a way I can update the config or other files to run everything offline? Thanks.

Cannot access gated repo for url https://huggingface.co/stabilityai/japanese-stablelm-instruct-alpha-7b/resolve/main/configuration_japanese_stablelm_alpha.py. Repo model stabilityai/japanese-stablelm-instruct-alpha-7b is gated. You must be authenticated to access it.

leemeng

Aug 10, 2023

Hey thanks for reporting this issue.
Not 100% sure but maybe you need to first hugging login as the user who get the repo access?
And since gated mechanism is implemented by HF you might need to ask in their forum since we might not be able to help on this.

SenY

Aug 10, 2023

Required login.

huggingface-cli login

And input your token.

ZUNDOKO3

Aug 12, 2023

入手したトークンはどのファイルに書き込めばいいの？

chigaijin changed discussion status to closed Aug 12, 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