Interplay-AppCoder LLM outperforms leading coding LLM WizardCoder, earning a 440% higher functionality & 52% higher usefulness score, making it the top choice for developers & businesses
Iterate.ai, whose AI innovation ecosystem enables enterprises to build production-ready applications, announced the availability of Interplay-AppCoder LLM, the company’s large language model for automated code generation.
Code-generation LLMs have become an essential part of the software developers’ toolbox and a growing necessity for businesses looking to incorporate AI applications, improve their operations and stay ahead of their competitors. However, Iterate recognized that existing LLMs including ChatGPT do not support the most modern code-sets like LangChain, nor do they include the latest thinking around coding methodologies.
The arrival of Interplay-AppCoder LLM changes this situation.
“Our venture into training a code generation LLM on state-of-the-art generative AI frameworks and libraries like YOLO V8, LangChain, and VertexAI, has culminated in Interplay-AppCoder LLM,” states Brian Sathianathan, Iterate.ai’s CTO and Co-Founder. “The creation of Interplay-AppCoder LLM was made possible by the meticulous fine-tuning of CodeLlama-7B, 34B and Wizard Coder-15B, 34B on a bespoke dataset. Essentially, we are creating our own, updated version of ChatGPT specifically for developers to generate code at an enterprise level at levels that exceed what is currently available.”
Other leading coding models include Meta’s Code Llama, the AI model built on top of Meta’s Llama 2 LLM and fine-tuned for code generation and discussion, and WizardCoder, an open-source coding assistant. As of mid-October 2023, WizardCoder stood as the dominant coding LLM, soundly beating Code Llama in testing. Now, the newly launched Interplay-AppCoder LLM vastly out-codes WizardCoder.
Interplay-AppCoder LLM was created through meticulous fine-tuning of CodeLlama-7B, 34B and Wizard Coder-15B, 34B on a bespoke dataset of newer generative AI libraries such as LangChain, YOLO V8, and Vertex AI. The first release of the Interplay-AppCoder model’s performance scored high on the ICE Benchmark, a methodology that focuses on usefulness and functionality:
- Usefulness – 2.968 of 4.0 (52% higher than WizardCoder which scored 1.825)
- Functionality – 2.476 of 4.0 (440% higher than WizardCoder which scored 0.603)
Developers can test Interplay-AppCoder LLM at https://appcoder.interplay.iterate.ai/.
The Value of Interplay-AppCoder LLM
Businesses and software teams can use Iterate’s Interplay-AppCoder to write software faster and to check code effectiveness as if another software developer is sitting over the coder’s shoulder. AppCoder LLM can also be used on private servers, meaning private work has no chance of leaking into the Internet. This means that it is a critical advantage across all of an enterprise’s departments, not just IT development teams.
Jon Nordmark, CEO of Iterate.ai says, “This is not just a CIO issue for building Generative AI applications. Having a robust code generation LLM is important for digital teams and C-Suites to bring engaging generative AI digital applications to market faster.”
Deploying Iterate’s new LLM for code generation underscores a significant reduction in development time and resources, thus translating into substantial cost savings and enhanced productivity.
“Businesses can harness Interplay-AppCoder to stay ahead of the competition. Companies need the best tools available to them to work with generative AI, and the current leader is Iterate’s Interplay-AppCoder, which reduces time-to-market by automating code generation and extending support for the latest models and libraries. By automating the coding process, businesses can spend their time and resources focusing on strategic initiatives, fostering innovation and growth,” Sathianathan states.
Iterate.ai is constantly beating benchmarks and will always continue to innovate, which is necessary for success in this AI space.
Currently, Iterate.ai is building several private LLMs for large enterprises in the United States and Asia. The generative AI market worldwide is projected to reach $191.8 billion by 2032, growing at a CAGR of 34.1% from 2023 to 2032. Generative AI is expected to represent about 15% of the total AI market.