{ "architectures": [ "FlexOlmoForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "clip_qkv": null, "dtype": "float32", "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 64, "initializer_range": 0.02, "intermediate_size": 128, "max_position_embeddings": 4096, "model_type": "flex_olmo", "norm_topk_prob": false, "num_attention_heads": 4, "num_experts": 4, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 2, "output_router_logits": false, "pad_token_id": 100277, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 500000, "rope_type": "default" }, "rope_theta": 500000, "router_aux_loss_coef": 0.01, "tie_word_embeddings": false, "transformers_version": "5.0.0.dev0", "use_cache": true, "vocab_size": 100352 }