Instructions to use saberai/Zro1.5_3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use saberai/Zro1.5_3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="saberai/Zro1.5_3B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("saberai/Zro1.5_3B") model = AutoModelForCausalLM.from_pretrained("saberai/Zro1.5_3B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use saberai/Zro1.5_3B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "saberai/Zro1.5_3B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "saberai/Zro1.5_3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/saberai/Zro1.5_3B
- SGLang
How to use saberai/Zro1.5_3B 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 "saberai/Zro1.5_3B" \ --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": "saberai/Zro1.5_3B", "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 "saberai/Zro1.5_3B" \ --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": "saberai/Zro1.5_3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use saberai/Zro1.5_3B with Docker Model Runner:
docker model run hf.co/saberai/Zro1.5_3B
Introducing Zro1.5_3B by Saber AI โ Precision and Performance in a Compact Package, fine-tuned for enhanced reasoning and mathematical skills on low-powered mobile devices.
Key Features:
Efficient Precision: Zro1.5_3B excels in capturing nuances despite its compact size, making it a powerful Small Language Model (SLM).
Resource Optimization: Maximized efficiency without sacrificing performance, ensuring seamless integration into diverse platforms.
Adaptability: Customize parameters to tailor the model to your project's specific needs, offering flexibility and versatility.
Scalability: Designed to scale effortlessly, from small projects to large-scale applications.
Cutting-Edge Technology: Leverage the latest in natural language processing for state-of-the-art performance.
Reasoning Enhancement: Fine-tuned in RedPajama-INCITE-Chat-3B-v1 to improve reasoning skills and mathematical reasoning.
Mobile Optimization: Tailored for low-powered mobile devices, ensuring optimal performance on the go.
User-Friendly Integration: Effortless incorporation with comprehensive documentation and support.
Elevate your projects with Zro1.5_3B โ where small size meets unparalleled performance, specifically enhancing reasoning and mathematical skills on low-powered mobile devices.
- Downloads last month
- 218