Description
Ornith-1.5-122B is a highly capable member of the Ornith-1.5 family, designed to deliver exceptional performance in various benchmarks. It is a 122 billion parameter model optimized for efficient deployment on a single GPU, making it accessible for a wide range of applications. The model is particularly noted for its ability to follow instructions accurately, decompose tasks effectively, and understand real-world work scenarios. This makes it a valuable tool for developers and researchers looking to leverage advanced AI capabilities without the need for extensive computational resources.
Read More
The model's open weights are available under the MIT license, promoting open-source collaboration and innovation. It supports a context window of up to 262,144 tokens, which can be extended to approximately 1 million tokens using RoPE scaling. This flexibility allows users to handle large-scale tasks that require extensive input and output capabilities.
Ornith-1.5-122B is compatible with OpenAI's API, enabling seamless integration with existing AI frameworks and tools. It is optimized for terminal-based coding agents and can be used with various agent frameworks like Ollama, Atomic.chat, and Hermes Agent. The model's quantized variant, Ornith-1.5-122B-Mobile, extends its deployment capabilities to mobile devices, further broadening its applicability.
In terms of performance, Ornith-1.5-122B achieves impressive results across multiple benchmarks, including TerminalBench, CyberGym, and SWE-bench, among others. It consistently outperforms or matches other leading models in its class, demonstrating its efficiency and effectiveness in handling complex tasks.
- CategoryAI Models & LLMs
- Pricing ModelOpen source
- DeploymentCloud
- PlatformsWeb
Ornith-1.5-122B Highlights
122 billion parameters
Single-GPU deployment
Open-source under MIT license
Supports up to 262,144 token context window
Quantized mobile variant available
OpenAI API compatible
Optimized for terminal-based coding agents
State-of-the-art benchmark performance
Getting Started with Ornith-1.5-122B
Access model page: Visit the Hugging Face model card
Authenticate: Ensure you have the necessary credentials
Configure: Set up the model with recommended parameters
Send prompts: Use the API to interact with the model
Fine-tune: Adjust settings for specific tasks
Ornith-1.5-122B's Use Cases
- Efficient Deployment
- Mobile Applications
- Coding Assistance
- Real-World Scenarios
- Open-Source Projects
