config.json

{
    "architectures": [
        "MolmoForCausalLM"
    ],
    "attention_layer_norm": false,
    "auto_map": {
        "AutoConfig": "config_molmo.MolmoConfig",
        "AutoModelForCausalLM": "modeling_molmo.MolmoForCausalLM"
    },
    "clip_qkv": null,
    "embedding_size": 152064,
    "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,
    "quantization": {
        "group_size": 64,
        "bits": 8
    },
    "rope_theta": 1000000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "float32",
    "transformers_version": "4.43.3",
    "use_cache": true,
    "use_position_ids": true,
    "vision_config": {
        "skip_vision_non_divisible": true,
        "intermediate_size": 37888,
    },
    "vocab_size": 152064,
    "weight_tying": false
}