Instructions to use jjszpak/SCAN-exp1b-8proc-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jjszpak/SCAN-exp1b-8proc-v0 with Transformers:

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

pipe = pipeline("text-generation", model="jjszpak/SCAN-exp1b-8proc-v0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jjszpak/SCAN-exp1b-8proc-v0")
model = AutoModelForCausalLM.from_pretrained("jjszpak/SCAN-exp1b-8proc-v0", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jjszpak/SCAN-exp1b-8proc-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jjszpak/SCAN-exp1b-8proc-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jjszpak/SCAN-exp1b-8proc-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jjszpak/SCAN-exp1b-8proc-v0

SGLang

How to use jjszpak/SCAN-exp1b-8proc-v0 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 "jjszpak/SCAN-exp1b-8proc-v0" \
    --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": "jjszpak/SCAN-exp1b-8proc-v0",
		"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 "jjszpak/SCAN-exp1b-8proc-v0" \
        --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": "jjszpak/SCAN-exp1b-8proc-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jjszpak/SCAN-exp1b-8proc-v0 with Docker Model Runner:
```
docker model run hf.co/jjszpak/SCAN-exp1b-8proc-v0
```

jjszpak commited on Jan 16, 2024

Commit

077f8bb

verified ·

1 Parent(s): 36b0261

Training in progress, step 6000

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Jan16_14-24-50_7704ebccca00/events.out.tfevents.1705415091.7704ebccca00.941.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63b2eb4ea935a0c07032ff181caa358aaa15eafa92151d7356de97dada476c1c
 size 327661000

 version https://git-lfs.github.com/spec/v1
+oid sha256:209790fa1192ae12a5c5fd64bf7ff3de49849a694cf054b875cdbd81292c1528
 size 327661000

runs/Jan16_14-24-50_7704ebccca00/events.out.tfevents.1705415091.7704ebccca00.941.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d0baf998cd2aa5c0d06b3e30a6f2d5de7a58a07e742bf6200bfab0773e19291
-size 8207

 version https://git-lfs.github.com/spec/v1
+oid sha256:1369a0ff68c8ac5847c8aca915611ef38f42e244c2c9163ea3b083526fac6890
+size 8635