上海人工智能实验室——书生·浦语(InternLM) InternLM是在过万亿 token数据上训练的多语千亿参数基座模型。通过多阶段的渐进式训练,InternLM 基座模型具有较高的知识水平,在中英文阅读理解、推理任务等需要较强思维能力的场景下性能优秀,在多种面向人类设计的综合性
"model.layers.2.attention.wo.weight": "pytorch_model-00001-of-00002.bin", "model.layers.2.attention.wqkv.weight": "pytorch_model-00001-of-00002.bin", "model.layers.2.attention_norm.weight": "pytorch_model-00001-of-00002.bin", "model.layers.2.feed_forward.w1.weight": "pytorch_mo...