Instructions to use saberai/Zro1.5_3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

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
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Introducing Zro1.5_3B by Saber AI – 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 – where small size meets unparalleled performance, specifically enhancing reasoning and mathematical skills on low-powered mobile devices.

Downloads last month: 76

Safetensors

Model size

3B params

Tensor type

F32

Model tree for saberai/Zro1.5_3B

Quantizations

1 model