Instructions to use lab-ii/gemma-4b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lab-ii/gemma-4b-instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="lab-ii/gemma-4b-instruct")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("lab-ii/gemma-4b-instruct")
model = AutoModelForMultimodalLM.from_pretrained("lab-ii/gemma-4b-instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lab-ii/gemma-4b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lab-ii/gemma-4b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lab-ii/gemma-4b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lab-ii/gemma-4b-instruct

SGLang

How to use lab-ii/gemma-4b-instruct 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 "lab-ii/gemma-4b-instruct" \
    --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": "lab-ii/gemma-4b-instruct",
		"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 "lab-ii/gemma-4b-instruct" \
        --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": "lab-ii/gemma-4b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lab-ii/gemma-4b-instruct with Docker Model Runner:
```
docker model run hf.co/lab-ii/gemma-4b-instruct
```

suronek commited on Jan 10

Commit

6b573b9

verified ·

1 Parent(s): e909a63

Upload all_results.json

Browse files

Files changed (1) hide show

all_results.json +8 -0

all_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 3.0,
+    "total_flos": 7.76867645696736e+16,
+    "train_loss": 2.121323910710248,
+    "train_runtime": 3108.1718,
+    "train_samples_per_second": 9.99,
+    "train_steps_per_second": 0.624
+}