Instructions to use radi-cho/gemma-2-9b-FLUTE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use radi-cho/gemma-2-9b-FLUTE with Transformers:

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

pipe = pipeline("text-generation", model="radi-cho/gemma-2-9b-FLUTE")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("radi-cho/gemma-2-9b-FLUTE")
model = AutoModelForCausalLM.from_pretrained("radi-cho/gemma-2-9b-FLUTE")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use radi-cho/gemma-2-9b-FLUTE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "radi-cho/gemma-2-9b-FLUTE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "radi-cho/gemma-2-9b-FLUTE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/radi-cho/gemma-2-9b-FLUTE

SGLang

How to use radi-cho/gemma-2-9b-FLUTE 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 "radi-cho/gemma-2-9b-FLUTE" \
    --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": "radi-cho/gemma-2-9b-FLUTE",
		"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 "radi-cho/gemma-2-9b-FLUTE" \
        --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": "radi-cho/gemma-2-9b-FLUTE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use radi-cho/gemma-2-9b-FLUTE with Docker Model Runner:
```
docker model run hf.co/radi-cho/gemma-2-9b-FLUTE
```

	Wiki	C4	PIQA	ARC-E	ARC-C	HellaSwag	Wino	Avg.
Unquantized	6.88	10.12	81.39	87.37	61.35	61.23	74.27	73.12
W4G64	6.49	10.35	81.28	86.24	59.30	60.40	75.30	72.50
W3G64	7.06	11.14	80.52	83.16	55.46	58.28	72.69	70.02

Revisions available in this repository:

main (W4G64, scales learned);
nfl_w3g64 (W3G64, scales learned);

Evaluations are provided for models with learned scales.
Benchmark scores (zero-shot) are computed with lm-evaluation-harness.

Downloads last month: 5

Safetensors

Model size

3B params

Tensor type

F32

F16

I16

Collection including radi-cho/gemma-2-9b-FLUTE

Gemma FLUTE

Collection

4 items • Updated Aug 4, 2024 • 1