公开知识图谱记录
MiniMax-M1-40k
记录摘要
来源摘要：We introduce MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. MiniMax-M1 is powered by a hybrid Mixture-of-Experts (MoE) architecture combined with a lightning attention mechanism. The model is developed based on our previous MiniMax-Text-01 model, which contains a total of 456 billion parameters with 45.9 billion parameters activated per token. Consistent with MiniMax-Text-01, the M1 model natively supports a context length of 1 million tokens, 8x the context size of DeepSee
来自项目知识图谱的有来源实体；具体工具属性仍需补齐。
已记录信息
- 能力: text generation
- 集成: transformers integration
- 集成: safetensors integration
- 集成: vllm integration
- 许可: apache-2.0
- 支持类型: text input/output
资料覆盖
知识图谱当前记录了 9 个已知资料维度，另有 9 个维度尚未记录，关联 1 篇公开资料。这些数字只描述资料覆盖，不代表模型性能或适配性已经验证。
相关公开记录
- MiniMax — 研发
- MiniMax-M1 — 隶属