{ "_name_or_path": "allenai/OLMoE-1B-7B-0924", "architectures": [ "DenseBackwardOLMoEForCausalLM" ], "auto_map": { "AutoConfig": "configuration_densebackward_olmoe.DenseBackwardOLMoEConfig", "AutoModel": "modeling_densebackward_olmoe.DenseBackwardOLMoEForCausalLM", "AutoModelForCausalLM": "modeling_densebackward_olmoe.DenseBackwardOLMoEForCausalLM" }, "attention_bias": false, "attention_dropout": 0.0, "clip_qkv": null, "eos_token_id": 50279, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 1024, "max_position_embeddings": 4096, "model_type": "olmoe", "norm_topk_prob": false, "num_attention_heads": 16, "num_experts": 64, "num_experts_per_tok": 8, "num_hidden_layers": 16, "num_key_value_heads": 16, "output_router_logits": false, "pad_token_id": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "router_aux_loss_coef": 0.01, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.45.2", "use_cache": true, "vocab_size": 50304 }