Full Title: ⚡️ IBM Granite 3.0 8B Surpasses Llama 3.1 on OpenLLM Benchmark
Highlights
IBM’s Granite 3.0 introduces multiple language models ranging from 2B to 8B parameters, released under Apache 2.0 license. The models support 12 natural languages and 116 programming languages, trained on 12 trillion tokens using a novel two-stage approach. (View Highlight)
• Granite 3.0 8B scores 37.6 on OpenLLM Leaderboard, surpassing Llama 3.1 8B (37.3)
• Achieves 3-23x cost reduction vs larger models in production tests
• Delivers 2x latency improvement through speculative decoding
• Processes enterprise tasks with <1B parameters using MoE architecture
• Supports 128K context window (upcoming) (View Highlight)
New highlights added October 25, 2024 at 12:20 PM
Granite 3.0 8B achieves 37.6 score on OpenLLM Leaderboard, outperforming Llama 3.1 8B (37.3) and similar-sized Mistral/Meta models on RAG benchmarks. (View Highlight)
