Instructions to use Falcon2006VN/GPasT-small-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Falcon2006VN/GPasT-small-model with Transformers:

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

pipe = pipeline("text-generation", model="Falcon2006VN/GPasT-small-model")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Falcon2006VN/GPasT-small-model")
model = AutoModelForCausalLM.from_pretrained("Falcon2006VN/GPasT-small-model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Falcon2006VN/GPasT-small-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Falcon2006VN/GPasT-small-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Falcon2006VN/GPasT-small-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Falcon2006VN/GPasT-small-model

SGLang

How to use Falcon2006VN/GPasT-small-model 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 "Falcon2006VN/GPasT-small-model" \
    --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": "Falcon2006VN/GPasT-small-model",
		"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 "Falcon2006VN/GPasT-small-model" \
        --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": "Falcon2006VN/GPasT-small-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Falcon2006VN/GPasT-small-model with Docker Model Runner:
```
docker model run hf.co/Falcon2006VN/GPasT-small-model
```

Falcon2006VN commited on Mar 9, 2023

Commit

b341eeb

1 Parent(s): 7e72815

Delete tf_model.h5

Browse files

Files changed (1) hide show

tf_model.h5 +0 -3

tf_model.h5 DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c6aaeb338d7c4dffe5e1e0bba4d99fd6cc85a984117fe3d5a7eaeafde9ef7e73
-size 503288144