| { | |
| "architectures": [ | |
| "MolmoForConditionalGeneration" | |
| ], | |
| "image_token_index": 152069, | |
| "initializer_range": 0.02, | |
| "model_type": "molmo", | |
| "pad_token_id": 152070, | |
| "pooling_config": { | |
| "attention_dropout": 0.0, | |
| "head_dim": 64, | |
| "hidden_size": 2048, | |
| "image_feature_dropout": 0.0, | |
| "image_num_patches": 24, | |
| "image_padding_embed": "pad_and_partial_pad", | |
| "image_pooling_type": "attention_meanq", | |
| "initializer_range": 0.02, | |
| "model_type": "", | |
| "num_attention_heads": 16, | |
| "num_key_value_heads": 16, | |
| "pad_embed_dim": 2048, | |
| "pooling_height": 2, | |
| "pooling_width": 2, | |
| "projector_hidden_act": "silu", | |
| "text_hidden_size": 8192, | |
| "text_intermediate_size": 59392, | |
| "torch_dtype": "bfloat16" | |
| }, | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "input_activations": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": true, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": null, | |
| "observer_kwargs": {}, | |
| "strategy": "token", | |
| "symmetric": true, | |
| "type": "float" | |
| }, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": "minmax", | |
| "observer_kwargs": {}, | |
| "strategy": "channel", | |
| "symmetric": true, | |
| "type": "float" | |
| } | |
| } | |
| }, | |
| "format": "float-quantized", | |
| "global_compression_ratio": null, | |
| "ignore": [ | |
| "model.vision_tower.vision_model.embeddings.patch_embedding", | |
| "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.0.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.0.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.1.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.1.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.2.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.2.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.3.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.3.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.4.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.4.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.5.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.5.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.6.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.6.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.7.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.7.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.8.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.8.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.9.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.9.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.10.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.10.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.11.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.11.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.12.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.12.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.13.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.13.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.14.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.14.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.15.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.15.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.16.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.16.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.17.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.17.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.18.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.18.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.19.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.19.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.20.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.20.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.21.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.21.mlp.fc2", | |
| "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj", | |
| "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj", | |
| "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj", | |
| "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj", | |
| "model.vision_tower.vision_model.encoder.layers.22.mlp.fc1", | |
| "model.vision_tower.vision_model.encoder.layers.22.mlp.fc2", | |
| "model.adapter.image_pooling_2d.k_proj", | |
| "model.adapter.image_pooling_2d.v_proj", | |
| "model.adapter.image_pooling_2d.q_proj", | |
| "model.adapter.image_pooling_2d.o_proj", | |
| "model.adapter.multi_modal_projector.linear_1", | |
| "model.adapter.multi_modal_projector.linear_3", | |
| "model.adapter.multi_modal_projector.linear_2", | |
| "lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "compressed" | |
| }, | |
| "text_config": { | |
| "additional_embedding_size": 0, | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "head_dim": 128, | |
| "hidden_act": "swiglu", | |
| "hidden_size": 8192, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 59392, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 4096, | |
| "model_type": "molmo_text", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 80, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 152070, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 4096, | |
| "torch_dtype": "bfloat16", | |
| "use_attention_layer_norm": false, | |
| "use_cache": true, | |
| "use_postnorm": false, | |
| "use_qk_norm": false, | |
| "vocab_size": 152071 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.0.dev0", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "hidden_act": "quick_gelu", | |
| "hidden_size": 1024, | |
| "image_size": 576, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layer_norm_eps": 1e-05, | |
| "model_type": "molmo_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 23, | |
| "num_image_positions": 577, | |
| "num_key_value_heads": 16, | |
| "patch_size": 14, | |
| "torch_dtype": "bfloat16" | |
| }, | |
| "vision_feature_layers": [ | |
| -2, | |
| -9 | |
| ], | |
| "vision_feature_select_strategy": "default", | |
| "vocab_size": 152071 | |
| } |