{ "architectures": [ "GptOssModel" ], "attention_bias": true, "attention_dropout": 0.0, "bos_token_id": 199998, "dtype": "float32", "eos_token_id": 200002, "head_dim": 16, "hidden_act": "gelu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 32, "layer_types": [ "sliding_attention", "full_attention" ], "max_position_embeddings": 512, "model_type": "gpt_oss", "num_attention_heads": 2, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 2, "num_local_experts": 8, "output_router_logits": false, "pad_token_id": 199999, "rms_norm_eps": 1e-05, "rope_parameters": { "beta_fast": 32.0, "beta_slow": 1.0, "factor": 32.0, "original_max_position_embeddings": 4096, "rope_theta": 150000.0, "rope_type": "yarn", "truncate": false }, "router_aux_loss_coef": 0.001, "sliding_window": 128, "tie_word_embeddings": false, "transformers_version": "5.16.0.dev0", "use_cache": true, "vocab_size": 200019 }