News from the AI & ML world
DeeperML
Alyssa Mazzina@RunPod Blog
//
San Francisco-based Deep Cogito, backed by RunPod, has unveiled Cogito v1, a family of open-source AI models ranging in size from 3B to 70B parameters. These models are designed to outperform leading alternatives, including those from LLaMA, DeepSeek, and Qwen, across standard benchmarks. The company emphasized that its AI models display both outstanding performance and efficiency which challenges the conventional secrecy surrounding AI advancements.
Cogito v1 models are trained using Iterated Distillation and Amplification (IDA), a novel alignment strategy. Instead of simply distilling from a larger teacher model, which can limit performance, IDA employs compute-intensive subroutines to generate improved answers, then distills this enhanced reasoning back into the model's parameters. This allows the model to learn how to think more effectively, rather than simply mimicking existing patterns. According to founder Drishan Arora, this method uses reasoning to improve the model’s intuition, leading to better decision-making when solving complex problems.
The Cogito v1 models support both Direct Mode for fast, high-quality completions of common tasks and Reasoning Mode for slower, more thoughtful responses using added compute. The 70B model, trained on RunPod using H200 GPUs, has demonstrated superior performance compared to LLaMA 3.3 70B and even the 109B LLaMA 4 Scout model across major benchmarks. Further development includes future checkpoints and larger Mixture of Experts (MoE) models with up to 671B parameters.
ImgSrc: blog.runpod.io
References :
Cogito v1 models are trained using Iterated Distillation and Amplification (IDA), a novel alignment strategy. Instead of simply distilling from a larger teacher model, which can limit performance, IDA employs compute-intensive subroutines to generate improved answers, then distills this enhanced reasoning back into the model's parameters. This allows the model to learn how to think more effectively, rather than simply mimicking existing patterns. According to founder Drishan Arora, this method uses reasoning to improve the model’s intuition, leading to better decision-making when solving complex problems.
The Cogito v1 models support both Direct Mode for fast, high-quality completions of common tasks and Reasoning Mode for slower, more thoughtful responses using added compute. The 70B model, trained on RunPod using H200 GPUs, has demonstrated superior performance compared to LLaMA 3.3 70B and even the 109B LLaMA 4 Scout model across major benchmarks. Further development includes future checkpoints and larger Mixture of Experts (MoE) models with up to 671B parameters.
ImgSrc: blog.runpod.io
Share:
References :
- bdtechtalks.com: Here is how DeepSeek models disrupted AI norms and revealed that outstanding performance and efficiency don’t require secrecy The post first appeared on .
- RunPod Blog: At RunPod, we're proud to power the next generation of AI breakthroughs—and this one is big. San Francisco-based Deep Cogito has just released Cogito v1, a family of open-source models ranging from 3B to 70B parameters. Each model outperforms leading alternatives from LLaMA, DeepSeek, and Qwen
- bdtechtalks.com: Bdtechtalks discusses the innovations powering DeepSeek's AI breakthrough.
- www.artificialintelligence-news.com: Artificial Intelligence News reports on DeepSeek's AI breakthrough in teaching machines what humans really want.
Classification:
- HashTags: #AI #DeepSeek #OpenSource
- Company: DeepSeek
- Target: AI Researchers
- Product: AI Models
- Feature: Open Source AI Models
- Type: AI
- Severity: Informative