Downloads · 30 days
9
22% of all-time downloads
sail-ai/sail-01
sail-01 is a machine learning model from sail-ai. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Sail-01 is a cutting-edge artificial intelligence model developed by Sail AI in collaboration with Ozone AI. Built upon the foundation of Reka Flash 3.0, Sail-01 delivers performance nearly on-par with top-tier models…
Downloads · 30 days
9
22% of all-time downloads
All-time downloads
41
Public
Parameters
20.9B
41.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors41.8 GB · 100%
From the Hugging Face model README
Sail-01 is a cutting-edge artificial intelligence model developed by Sail AI in collaboration with Ozone AI. Built upon the foundation of Reka Flash 3.0, Sail-01 delivers performance nearly on-par with top-tier models like QWQ-32B. It has been trained using distilled data from advanced models, including O3 Mini and GPT-4.5 Preview, enabling it to excel in a wide range of tasks, from natural language understanding to complex reasoning and generation.
To use Sail-01, follow these steps:
Install Dependencies: Ensure you have Python 3.8+ installed, then install the required dependencies. Sail-01 is compatible with the Hugging Face Transformers library:
pip install transformers torch safetensors
Download the Model: Sail-01 is hosted on Hugging Face. You can download the model weights and configuration files directly from the Hugging Face repository.
Below is a basic example of how to load and use Sail-01 for text generation using the Hugging Face Transformers library:
from transformers import AutoModelForCausalLM, AutoTokenizer
# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("sail-ai/sail-01")
model = AutoModelForCausalLM.from_pretrained("sail-ai/sail-01")
# Prepare input
prompt = "What is the future of artificial intelligence?"
inputs = tokenizer(prompt, return_tensors="pt")
# Generate text
outputs = model.generate(**inputs, max_length=200, temperature=0.7)
# Decode and print the output
output_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(output_text)
Sail-01 can be fine-tuned for specific tasks using the Hugging Face Transformers library. Refer to the Hugging Face documentation for detailed instructions on fine-tuning models with your own datasets.
Sail-01 is released under the SailLM License, a custom license developed by Sail AI. Key terms include:
For the full terms, please see the LICENSE.md file included in this repository.
Contributions to Sail-01 are not currently accepted, as this is a proprietary model released under the SailLM License. For suggestions, feedback, or inquiries, please refer to the official Sail AI or Ozone AI communication channels (to be provided).
Sail-01 builds upon the advancements of Reka Flash 3.0 and leverages distilled data from O3 Mini and GPT-4.5 Preview. We thank the broader AI research community for their contributions to the field, which have made models like Sail-01 possible. Special thanks to Ozone AI for their collaboration in developing this model.
Sail-01 is provided "as is" without warranty of any kind. Sail AI and Ozone AI are not liable for any damages arising from the use of this model. See the LICENSE.md file for full details.