Instructions to use yam-peleg/gemma-7b-experiment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yam-peleg/gemma-7b-experiment with Transformers:

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

pipe = pipeline("text-generation", model="yam-peleg/gemma-7b-experiment")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yam-peleg/gemma-7b-experiment")
model = AutoModelForCausalLM.from_pretrained("yam-peleg/gemma-7b-experiment")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use yam-peleg/gemma-7b-experiment with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yam-peleg/gemma-7b-experiment"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yam-peleg/gemma-7b-experiment",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yam-peleg/gemma-7b-experiment

SGLang

How to use yam-peleg/gemma-7b-experiment 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 "yam-peleg/gemma-7b-experiment" \
    --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": "yam-peleg/gemma-7b-experiment",
		"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 "yam-peleg/gemma-7b-experiment" \
        --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": "yam-peleg/gemma-7b-experiment",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yam-peleg/gemma-7b-experiment with Docker Model Runner:
```
docker model run hf.co/yam-peleg/gemma-7b-experiment
```

gemma-7b-experiment

This is just an experiment placeholder for testing out local validation strategy, there is absolutly no real reason for you to try this model. it has nothing new into it.

An experiment for testing and refining a local cross validation strategy.

The goal is to evaluate LLMs locally and make sure the scores obtained locally can be reproduced publiclly.

More details coming soon.

license: apache-2.0

Downloads last month: 63

Safetensors

Model size

9B params

Tensor type

BF16