Trending blocks

拥有 30 亿参数的多语言大型语言模型，专为高级自然语言处理任务（如对话生成、推理和总结）而优化。该模型采用最新的 Transformer 架构，支持包括英语、西班牙语和印地语在内的八种语言，并可以适配其他语言。 Llama 3.2 3B 模型基于 9 万亿标记进行训练，在遵循指令、复杂推理和工具使用方面表现出色。其平衡的性能使其成为在多语言环境中需要文本生成的准确性和效率的应用场景的理想选择。

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

Refactor the selected code to be more idiomatic and maintainable

OpenAI's fast, affordable small model for focused tasks

William Shakespeare takes to the IDE as your coding assistant

Mi prompt

Ground rules for concise to point of the problem

Meta最新一代的Llama 3.1模型系列，8B（80亿参数）的指令微调版本特别快速高效。在业界评估中，表现出强劲的性能，超越了很多领先的闭源模型。

test

K3D Docs

Cutting-edge language model for coding. With the second version released January 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.