{ "architectures": [ "MolmoAudioForCausalLM" ], "attention_layer_norm": false, "audio_codebook_offset": 152072, "audio_codebook_size": 2048, "audio_max_input_tokens": 1024, "audio_pad_token_id": 152071, "auto_map": { "AutoConfig": "config_molmo.MolmoConfig", "AutoModelForCausalLM": "modeling_molmo.MolmoForCausalLM" }, "clip_qkv": null, "dtype": "bfloat16", "embedding_size": 154124, "eoa_token_id": 152070, "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 37888, "layer_norm_eps": 1e-06, "layer_norm_type": "rms", "max_position_embeddings": 4096, "model_type": "molmo", "norm_after": false, "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "qkv_bias": true, "rope_theta": 1000000.0, "soa_token_id": 152069, "spk_token_ids": [ 154120, 154121, 154122, 154123 ], "tie_word_embeddings": false, "transformers_version": "4.43.3", "use_cache": true, "use_position_ids": true, "vocab_size": 154124, "weight_tying": false }