Instructions to use shy-schini/gemma-sprint-get-to-the-point with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shy-schini/gemma-sprint-get-to-the-point with Transformers:

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

pipe = pipeline("text-generation", model="shy-schini/gemma-sprint-get-to-the-point")

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

tokenizer = AutoTokenizer.from_pretrained("shy-schini/gemma-sprint-get-to-the-point")
model = AutoModelForCausalLM.from_pretrained("shy-schini/gemma-sprint-get-to-the-point", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use shy-schini/gemma-sprint-get-to-the-point with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/shy-schini/gemma-sprint-get-to-the-point

SGLang

How to use shy-schini/gemma-sprint-get-to-the-point 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 "shy-schini/gemma-sprint-get-to-the-point" \
    --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": "shy-schini/gemma-sprint-get-to-the-point",
		"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 "shy-schini/gemma-sprint-get-to-the-point" \
        --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": "shy-schini/gemma-sprint-get-to-the-point",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use shy-schini/gemma-sprint-get-to-the-point with Docker Model Runner:
```
docker model run hf.co/shy-schini/gemma-sprint-get-to-the-point
```

Model Card for Model ID

** Summarize financial articles

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: Sh Yang
Activity with: Goolge MLB 2024
Model type: Language Model
Finetuned from model [optional]: google/gemma2-2b-it
Language: English
Dataset: Lightscale/financial-advise-summarization

Downloads last month: 15

Safetensors

Model size

3B params

Tensor type

F32

shy-schini
/

gemma-sprint-get-to-the-point

Model Card for Model ID

Dataset used to train shy-schini/gemma-sprint-get-to-the-point