IBM rolls-out Granite 3.0
Tech giant IBM Monday Oct 21, 2024 announced the launch of Granite 3.0, its most advanced family of AI models to date
Armonk (New York): Tech giant IBM Monday Oct 21, 2024 announced the launch of Granite 3.0, its most advanced family of AI models to date.
IBM launched Granite 3.0 at its annual TechXchange event.
IBM's third-generation Granite flagship language models can outperform or match similarly sized models from leading model providers on many academic and industry benchmarks, showcasing strong performance, transparency and safety.
"The Granite models are released under the permissive Apache 2.0 license, making them unique in the combination of performance, flexibility and autonomy they provide to enterprise clients and the community at large", IBM said.
"Workhorse Models"
The new Granite 3.0 8B and 2B language models are designed as 'workhorse' models for enterprise AI, delivering strong performance for tasks such as Retrieval Augmented Geneneration (RAG), classification, summarization, entity extraction, and tool use.
"These compact, versatile models are designed to be fine-tuned with enterprise data and seamlessly integrated across diverse business environments or workflows", IBM said.
While many large language models (LLMs) are trained on publicly available data, a vast majority of enterprise data remains untapped.
"By combining a small Granite model with enterprise data, especially using the revolutionary alignment technique InstructLab – introduced by IBM and RedHat in May – IBM believes businesses can achieve task-specific performance that rivals larger models at a fraction of the cost (based on an observed range of 3x-23x less cost than large frontier models in several early proofs-of-concept1)", the tech giant said.
Granite 3.0 Features
- New Granite 3.0 8B & 2B models, released under the permissive Apache 2.0 license, show strong performance across many academic and enterprise benchmarks, able to outperform or match similar-sized models
- New Granite Guardian 3.0 models deliver IBM's most comprehensive guardrail capabilities to advance safe and trustworthy AI
- New Granite 3.0 Mixture-of-Experts models enable extremely efficient inference and low latency, suitable for CPU-based deployments and edge computing
- New Granite Time Series model achieved state-of-the-art performance in zero/few-shot forecasting, outperforming models 10 times larger
- IBM unveils next generation of Granite-powered watsonx Code Assistant for general purpose coding; Debuts new tools in watsonx.ai for building and deploying AI applications and agents
- Announces Granite will become the default model of Consulting Advantage, an AI-powered delivery platform used by IBM's 160,000 consultants to bring new solutions to clients faster
Granite 3.0 benchmarks
The Granite 3.0 language models also demonstrate promising results on raw performance.
"On standard academic benchmarks defined by Hugging Face's OpenLLM Leaderboard, the Granite 3.0 8B Instruct model's overall performance leads on average against state-of-the-art-performance of similar-sized open source models from Meta and Mistral", IBM said.
"On IBM's state-of-the-art AttaQ safety benchmark, the Granite 3.0 8B Instruct model leads across all measured safety dimensions compared to models from Meta and Mistral", the company said.
Granite Guardian 3.0
On Monday, IBM also introduced a new family of Granite Guardian models that permit application developers to implement safety guardrails by checking user prompts and LLM responses for a variety of risks.
"The Granite Guardian 3.0 8B and 2B models provide the most comprehensive set of risk and harm detection capabilities available in the market today", IBM said.
In addition to harm dimensions such as social bias, hate, toxicity, profanity, violence, jailbreaking and more, these models also provide a range of unique RAG-specific checks such as groundedness, context relevance, and answer relevance.
In extensive testing across 19 safety and RAG benchmarks, the Granite Guardian 3.0 8B model has higher overall accuracy on harm detection on average than all three generations of Llama Guard models from Meta. It also showed on par overall performance in hallucination detection on average with specialized hallucination detection models WeCheck and MiniCheck.
While the Granite Guardian models are derived from the corresponding Granite language models, they can be used to implement guardrails alongside any open or proprietary AI models.
Follow ummid.com WhatsApp Channel for all the latest updates.
Select Language To Read in Urdu, Hindi, Marathi or Arabic.
Post Comments