Search Results for "task" - Page 2

...It operates in OpenAI’s Harmony response format and can be deployed via Transformers, vLLM, Ollama, LM Studio, and PyTorch. Developers can control the reasoning level (low, medium, high) to balance speed and depth depending on the task. Released under the Apache 2.0 license, it enables both commercial and research applications. The model supports function calling, web browsing, and code execution, streamlining intelligent agent development.

MiniMax-M2.7 is a large-scale open-weight language model designed for advanced agent-based workflows, professional software engineering, and complex productivity tasks. With 229B parameters, it introduces a self-evolution framework in which the model actively improves its own capabilities by updating memory, generating skills, and iterating through reinforcement learning experiments. This process enables it to autonomously refine systems, achieving measurable performance gains such as a 30%...

...The model excels at non-standard layouts and complex table structures, outperforming non-reasoning OCR systems like GPT-4o and OCRFlux, and competing with large closed-source reasoning models like Gemini 2.5. Thinking token usage can range from 20% to 500% of the final answer, depending on task difficulty. NuMarkdown-8B-Thinking is released under the MIT license and supports vLLM and Transformers for deployment.

...Built on a Mixture-of-Experts architecture with approximately 309B total parameters and around 15B activated per inference, it balances high capability with efficient execution. The model natively processes text, images, video, and audio within a unified system, enabling cross-modal understanding and complex task execution in a single pipeline. With a context window of up to 1 million tokens, it can handle large documents, extended conversations, and multi-step workflows without fragmentation. MiMo-V2.5 delivers near-Pro-level performance in coding, reasoning, and agent tasks while maintaining lower cost and faster inference speeds. It also integrates advanced components such as multi-token prediction modules and specialized vision and audio encoders, making it well-suited for autonomous agents and software development.

...DeepSeek-V4-Pro is positioned as the high-end variant of the V4 family, outperforming most open-source models in areas such as agentic coding, STEM reasoning, and world knowledge, and approaching the performance of leading closed-source systems. It also supports advanced reasoning modes and tool-based workflows, enabling autonomous task execution.

...The model was notably used in competitive AI challenges such as the 2025 International Mathematical Olympiad (IMO) and IOI, achieving top-tier results. DeepSeek-V3.2 also features a large-scale agentic task synthesis pipeline, which generates training data to enhance tool-use intelligence and multi-step reasoning. It introduces a new “thinking with tools” chat template, allowing it to reason and decide when to invoke specific tools during problem solving.

Kimi K2.7 Code is a coding-focused agentic model built on Kimi K2.6, designed for long-horizon software engineering, autonomous coding workflows, and complex tool-based execution. It improves end-to-end task completion across real-world programming scenarios while reducing thinking-token usage by about 30% compared with K2.6. Architecturally, it uses a 1T-parameter Mixture-of-Experts design with 32B activated parameters, 61 layers, 384 experts, a 256K-token context window, and a MoonViT vision encoder. The model supports image and video input, native INT4 quantization, interleaved thinking, and multi-step tool calling. ...

Ministral 3 8B Base 2512 is a mid-sized, dense model in the Ministral 3 series, designed as a general-purpose foundation for text and image tasks. It pairs an 8.4B-parameter language model with a 0.4B-parameter vision encoder, enabling unified multimodal capabilities out of the box. As a “base” model (i.e., not fine-tuned for instruction or reasoning), it offers a flexible starting point for custom downstream tasks or fine-tuning. The model supports a large 256k token context window, making...