Instructions to use BINARIAL/GALIA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BINARIAL/GALIA with Transformers:

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

pipe = pipeline("text-generation", model="BINARIAL/GALIA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("BINARIAL/GALIA", device_map="auto")

PEFT
How to use BINARIAL/GALIA with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BINARIAL/GALIA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BINARIAL/GALIA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BINARIAL/GALIA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BINARIAL/GALIA

SGLang

How to use BINARIAL/GALIA 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 "BINARIAL/GALIA" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BINARIAL/GALIA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "BINARIAL/GALIA" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BINARIAL/GALIA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BINARIAL/GALIA with Docker Model Runner:
```
docker model run hf.co/BINARIAL/GALIA
```

Rodrigo-Binarial commited on Mar 26, 2024

Commit

3b64a03

verified ·

1 Parent(s): 72d6afe

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

runs/Mar26_16-21-29_r-binarial-tech-ai-9uu5twdo-fb086-rmjvv/events.out.tfevents.1711470113.r-binarial-tech-ai-9uu5twdo-fb086-rmjvv.106.0 +2 -2

runs/Mar26_16-21-29_r-binarial-tech-ai-9uu5twdo-fb086-rmjvv/events.out.tfevents.1711470113.r-binarial-tech-ai-9uu5twdo-fb086-rmjvv.106.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb9f1981ac26acf5bf455ef81a3b4d31f9b95470d1fa4962a89a138ccb903db
-size 67536

 version https://git-lfs.github.com/spec/v1
+oid sha256:6aede78751be83aee0f498664c8b0a2e9ce7921f0a9f725eaefd2cbca3130533
+size 67747