Platypus 2 70B AI LLM tops HuggingFace Open LLM leaderboard

Share post:

A new open source large language model (LLM) called Platypus 2 has topped the HuggingFace Open LLM Leaderboard.

Platypus 2 is a 70B parameter model that has been fine-tuned on a carefully curated dataset of STEM and logic questions. It is able to achieve state-of-the-art performance on a variety of benchmarks, including question answering, summarization, and translation.

The Platypus 2 model was developed by a team of researchers at Google AI.

The team used a variety of techniques like curated dataset of STEM and logic questions, low-rank approximation technique called LoRA to reduce the number of parameters in the model, and a parameter-efficient fine-tuning technique called PEFT to improve the performance of the model.

The Platypus 2 model is the first open source LLM to achieve state-of-the-art performance on a variety of benchmarks. The model is also efficient to train and deploy, making it a valuable tool for a wide range of applications.

The developers of Platypus 2 also advised that safety testing should be conducted before deploying the model. This is due to the potential misuse of the model for malicious activities. Users are also advised to ensure that the model is not trained on data that could be used to bias its results.

The Platypus 2 model is available for download on the Google AI website. The website also includes more information about the model, including the papers, code, and dataset used to train it.

The sources for this piece include an article in GeekyGadgets.

SUBSCRIBE NOW

Related articles

Research Raises Concerns Over AI Impact on Code Quality

Recent findings from GitClear, a developer analytics firm, indicate that the increasing reliance on AI assistance in software...

Microsoft to train 100,000 Indian developers in AI

Microsoft has launched an ambitious program called "AI Odyssey" to train 100,000 Indian developers in artificial intelligence by...

NIST issues cybersecurity guide for AI developers

Paper identifies the types of cyberattacks that can manipulate the behavior of artificial intelligen

Canada, U.S. sign international guidelines for safe AI development

Eighteen countries, including Canada, the U.S. and the U.K., today agreed on recommended guidelines to developers in their nations for the secure design, development, deployment, and operation of artificial intelligent systems. It’s the latest in a series of voluntary guardrails that nations are urging their public and private sectors to follow for overseeing AI in

Become a member

New, Relevant Tech Stories. Our article selection is done by industry professionals. Our writers summarize them to give you the key takeaways