| { |
| "architectures": [ |
| "Lfm2VlForConditionalGeneration" |
| ], |
| "do_image_splitting": true, |
| "downsample_factor": 2, |
| "dtype": "bfloat16", |
| "encoder_patch_size": 16, |
| "image_token_id": 396, |
| "max_image_tokens": 256, |
| "max_pixels_tolerance": 2.0, |
| "max_tiles": 10, |
| "min_image_tokens": 64, |
| "min_tiles": 2, |
| "model_type": "lfm2_vl", |
| "projector_bias": true, |
| "projector_hidden_act": "gelu", |
| "projector_hidden_size": 2560, |
| "projector_use_layernorm": true, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": "pack-quantized", |
| "input_activations": null, |
| "output_activations": null, |
| "targets": [ |
| "model.vision_tower.embeddings.patch_embedding", |
| "model.vision_tower.encoder.layers.0.mlp.fc1", |
| "model.vision_tower.encoder.layers.0.mlp.fc2", |
| "model.vision_tower.encoder.layers.0.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.0.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.0.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.0.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.1.mlp.fc1", |
| "model.vision_tower.encoder.layers.1.mlp.fc2", |
| "model.vision_tower.encoder.layers.1.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.1.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.1.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.1.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.10.mlp.fc1", |
| "model.vision_tower.encoder.layers.10.mlp.fc2", |
| "model.vision_tower.encoder.layers.10.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.10.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.10.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.10.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.11.mlp.fc1", |
| "model.vision_tower.encoder.layers.11.mlp.fc2", |
| "model.vision_tower.encoder.layers.11.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.11.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.11.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.11.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.12.mlp.fc1", |
| "model.vision_tower.encoder.layers.12.mlp.fc2", |
| "model.vision_tower.encoder.layers.12.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.12.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.12.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.12.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.13.mlp.fc1", |
| "model.vision_tower.encoder.layers.13.mlp.fc2", |
| "model.vision_tower.encoder.layers.13.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.13.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.13.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.13.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.14.mlp.fc1", |
| "model.vision_tower.encoder.layers.14.mlp.fc2", |
| "model.vision_tower.encoder.layers.14.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.14.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.14.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.14.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.15.mlp.fc1", |
| "model.vision_tower.encoder.layers.15.mlp.fc2", |
| "model.vision_tower.encoder.layers.15.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.15.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.15.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.15.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.16.mlp.fc1", |
| "model.vision_tower.encoder.layers.16.mlp.fc2", |
| "model.vision_tower.encoder.layers.16.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.16.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.16.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.16.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.17.mlp.fc1", |
| "model.vision_tower.encoder.layers.17.mlp.fc2", |
| "model.vision_tower.encoder.layers.17.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.17.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.17.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.17.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.18.mlp.fc1", |
| "model.vision_tower.encoder.layers.18.mlp.fc2", |
| "model.vision_tower.encoder.layers.18.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.18.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.18.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.18.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.19.mlp.fc1", |
| "model.vision_tower.encoder.layers.19.mlp.fc2", |
| "model.vision_tower.encoder.layers.19.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.19.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.19.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.19.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.2.mlp.fc1", |
| "model.vision_tower.encoder.layers.2.mlp.fc2", |
| "model.vision_tower.encoder.layers.2.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.2.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.2.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.2.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.20.mlp.fc1", |
| "model.vision_tower.encoder.layers.20.mlp.fc2", |
| "model.vision_tower.encoder.layers.20.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.20.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.20.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.20.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.21.mlp.fc1", |
| "model.vision_tower.encoder.layers.21.mlp.fc2", |
| "model.vision_tower.encoder.layers.21.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.21.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.21.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.21.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.22.mlp.fc1", |
| "model.vision_tower.encoder.layers.22.mlp.fc2", |
| "model.vision_tower.encoder.layers.22.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.22.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.22.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.22.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.23.mlp.fc1", |
| "model.vision_tower.encoder.layers.23.mlp.fc2", |
| "model.vision_tower.encoder.layers.23.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.23.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.23.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.23.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.24.mlp.fc1", |
| "model.vision_tower.encoder.layers.24.mlp.fc2", |
| "model.vision_tower.encoder.layers.24.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.24.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.24.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.24.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.25.mlp.fc1", |
| "model.vision_tower.encoder.layers.25.mlp.fc2", |
| "model.vision_tower.encoder.layers.25.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.25.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.25.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.25.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.26.mlp.fc1", |
| "model.vision_tower.encoder.layers.26.mlp.fc2", |
| "model.vision_tower.encoder.layers.26.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.26.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.26.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.26.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.3.mlp.fc1", |
| "model.vision_tower.encoder.layers.3.mlp.fc2", |
| "model.vision_tower.encoder.layers.3.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.3.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.3.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.3.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.4.mlp.fc1", |
| "model.vision_tower.encoder.layers.4.mlp.fc2", |
| "model.vision_tower.encoder.layers.4.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.4.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.4.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.4.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.5.mlp.fc1", |
| "model.vision_tower.encoder.layers.5.mlp.fc2", |
| "model.vision_tower.encoder.layers.5.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.5.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.5.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.5.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.6.mlp.fc1", |
| "model.vision_tower.encoder.layers.6.mlp.fc2", |
| "model.vision_tower.encoder.layers.6.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.6.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.6.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.6.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.7.mlp.fc1", |
| "model.vision_tower.encoder.layers.7.mlp.fc2", |
| "model.vision_tower.encoder.layers.7.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.7.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.7.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.7.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.8.mlp.fc1", |
| "model.vision_tower.encoder.layers.8.mlp.fc2", |
| "model.vision_tower.encoder.layers.8.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.8.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.8.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.8.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.9.mlp.fc1", |
| "model.vision_tower.encoder.layers.9.mlp.fc2", |
| "model.vision_tower.encoder.layers.9.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.9.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.9.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.9.self_attn.v_proj" |
| ], |
| "weights": { |
| "actorder": "static", |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "channel", |
| "symmetric": true, |
| "type": "int", |
| "zp_dtype": null |
| } |
| }, |
| "group_1": { |
| "format": "pack-quantized", |
| "input_activations": null, |
| "output_activations": null, |
| "targets": [ |
| "model.language_model.layers.0.conv.in_proj", |
| "model.language_model.layers.0.conv.out_proj", |
| "model.language_model.layers.0.feed_forward.w1", |
| "model.language_model.layers.0.feed_forward.w2", |
| "model.language_model.layers.0.feed_forward.w3", |
| "model.language_model.layers.1.conv.in_proj", |
| "model.language_model.layers.1.conv.out_proj", |
| "model.language_model.layers.1.feed_forward.w1", |
| "model.language_model.layers.1.feed_forward.w2", |
| "model.language_model.layers.1.feed_forward.w3", |
| "model.language_model.layers.10.conv.in_proj", |
| "model.language_model.layers.10.conv.out_proj", |
| "model.language_model.layers.10.feed_forward.w1", |
| "model.language_model.layers.10.feed_forward.w2", |
| "model.language_model.layers.10.feed_forward.w3", |
| "model.language_model.layers.11.conv.in_proj", |
| "model.language_model.layers.11.conv.out_proj", |
| "model.language_model.layers.11.feed_forward.w1", |
| "model.language_model.layers.11.feed_forward.w2", |
| "model.language_model.layers.11.feed_forward.w3", |
| "model.language_model.layers.12.conv.in_proj", |
| "model.language_model.layers.12.conv.out_proj", |
| "model.language_model.layers.12.feed_forward.w1", |
| "model.language_model.layers.12.feed_forward.w2", |
| "model.language_model.layers.12.feed_forward.w3", |
| "model.language_model.layers.13.feed_forward.w1", |
| "model.language_model.layers.13.feed_forward.w2", |
| "model.language_model.layers.13.feed_forward.w3", |
| "model.language_model.layers.13.self_attn.k_proj", |
| "model.language_model.layers.13.self_attn.out_proj", |
| "model.language_model.layers.13.self_attn.q_proj", |
| "model.language_model.layers.13.self_attn.v_proj", |
| "model.language_model.layers.14.conv.in_proj", |
| "model.language_model.layers.14.conv.out_proj", |
| "model.language_model.layers.14.feed_forward.w1", |
| "model.language_model.layers.14.feed_forward.w2", |
| "model.language_model.layers.14.feed_forward.w3", |
| "model.language_model.layers.15.conv.in_proj", |
| "model.language_model.layers.15.conv.out_proj", |
| "model.language_model.layers.15.feed_forward.w1", |
| "model.language_model.layers.15.feed_forward.w2", |
| "model.language_model.layers.15.feed_forward.w3", |
| "model.language_model.layers.16.conv.in_proj", |
| "model.language_model.layers.16.conv.out_proj", |
| "model.language_model.layers.16.feed_forward.w1", |
| "model.language_model.layers.16.feed_forward.w2", |
| "model.language_model.layers.16.feed_forward.w3", |
| "model.language_model.layers.17.feed_forward.w1", |
| "model.language_model.layers.17.feed_forward.w2", |
| "model.language_model.layers.17.feed_forward.w3", |
| "model.language_model.layers.17.self_attn.k_proj", |
| "model.language_model.layers.17.self_attn.out_proj", |
| "model.language_model.layers.17.self_attn.q_proj", |
| "model.language_model.layers.17.self_attn.v_proj", |
| "model.language_model.layers.18.conv.in_proj", |
| "model.language_model.layers.18.conv.out_proj", |
| "model.language_model.layers.18.feed_forward.w1", |
| "model.language_model.layers.18.feed_forward.w2", |
| "model.language_model.layers.18.feed_forward.w3", |
| "model.language_model.layers.19.conv.in_proj", |
| "model.language_model.layers.19.conv.out_proj", |
| "model.language_model.layers.19.feed_forward.w1", |
| "model.language_model.layers.19.feed_forward.w2", |
| "model.language_model.layers.19.feed_forward.w3", |
| "model.language_model.layers.2.feed_forward.w1", |
| "model.language_model.layers.2.feed_forward.w2", |
| "model.language_model.layers.2.feed_forward.w3", |
| "model.language_model.layers.2.self_attn.k_proj", |
| "model.language_model.layers.2.self_attn.out_proj", |
| "model.language_model.layers.2.self_attn.q_proj", |
| "model.language_model.layers.2.self_attn.v_proj", |
| "model.language_model.layers.20.conv.in_proj", |
| "model.language_model.layers.20.conv.out_proj", |
| "model.language_model.layers.20.feed_forward.w1", |
| "model.language_model.layers.20.feed_forward.w2", |
| "model.language_model.layers.20.feed_forward.w3", |
| "model.language_model.layers.21.feed_forward.w1", |
| "model.language_model.layers.21.feed_forward.w2", |
| "model.language_model.layers.21.feed_forward.w3", |
| "model.language_model.layers.21.self_attn.k_proj", |
| "model.language_model.layers.21.self_attn.out_proj", |
| "model.language_model.layers.21.self_attn.q_proj", |
| "model.language_model.layers.21.self_attn.v_proj", |
| "model.language_model.layers.22.conv.in_proj", |
| "model.language_model.layers.22.conv.out_proj", |
| "model.language_model.layers.22.feed_forward.w1", |
| "model.language_model.layers.22.feed_forward.w2", |
| "model.language_model.layers.22.feed_forward.w3", |
| "model.language_model.layers.23.conv.in_proj", |
| "model.language_model.layers.23.conv.out_proj", |
| "model.language_model.layers.23.feed_forward.w1", |
| "model.language_model.layers.23.feed_forward.w2", |
| "model.language_model.layers.23.feed_forward.w3", |
| "model.language_model.layers.24.feed_forward.w1", |
| "model.language_model.layers.24.feed_forward.w2", |
| "model.language_model.layers.24.feed_forward.w3", |
| "model.language_model.layers.24.self_attn.k_proj", |
| "model.language_model.layers.24.self_attn.out_proj", |
| "model.language_model.layers.24.self_attn.q_proj", |
| "model.language_model.layers.24.self_attn.v_proj", |
| "model.language_model.layers.25.conv.in_proj", |
| "model.language_model.layers.25.conv.out_proj", |
| "model.language_model.layers.25.feed_forward.w1", |
| "model.language_model.layers.25.feed_forward.w2", |
| "model.language_model.layers.25.feed_forward.w3", |
| "model.language_model.layers.26.conv.in_proj", |
| "model.language_model.layers.26.conv.out_proj", |
| "model.language_model.layers.26.feed_forward.w1", |
| "model.language_model.layers.26.feed_forward.w2", |
| "model.language_model.layers.26.feed_forward.w3", |
| "model.language_model.layers.27.feed_forward.w1", |
| "model.language_model.layers.27.feed_forward.w2", |
| "model.language_model.layers.27.feed_forward.w3", |
| "model.language_model.layers.27.self_attn.k_proj", |
| "model.language_model.layers.27.self_attn.out_proj", |
| "model.language_model.layers.27.self_attn.q_proj", |
| "model.language_model.layers.27.self_attn.v_proj", |
| "model.language_model.layers.28.conv.in_proj", |
| "model.language_model.layers.28.conv.out_proj", |
| "model.language_model.layers.28.feed_forward.w1", |
| "model.language_model.layers.28.feed_forward.w2", |
| "model.language_model.layers.28.feed_forward.w3", |
| "model.language_model.layers.29.conv.in_proj", |
| "model.language_model.layers.29.conv.out_proj", |
| "model.language_model.layers.29.feed_forward.w1", |
| "model.language_model.layers.29.feed_forward.w2", |
| "model.language_model.layers.29.feed_forward.w3", |
| "model.language_model.layers.3.conv.in_proj", |
| "model.language_model.layers.3.conv.out_proj", |
| "model.language_model.layers.3.feed_forward.w1", |
| "model.language_model.layers.3.feed_forward.w2", |
| "model.language_model.layers.3.feed_forward.w3", |
| "model.language_model.layers.4.conv.in_proj", |
| "model.language_model.layers.4.conv.out_proj", |
| "model.language_model.layers.4.feed_forward.w1", |
| "model.language_model.layers.4.feed_forward.w2", |
| "model.language_model.layers.4.feed_forward.w3", |
| "model.language_model.layers.5.feed_forward.w1", |
| "model.language_model.layers.5.feed_forward.w2", |
| "model.language_model.layers.5.feed_forward.w3", |
| "model.language_model.layers.5.self_attn.k_proj", |
| "model.language_model.layers.5.self_attn.out_proj", |
| "model.language_model.layers.5.self_attn.q_proj", |
| "model.language_model.layers.5.self_attn.v_proj", |
| "model.language_model.layers.6.conv.in_proj", |
| "model.language_model.layers.6.conv.out_proj", |
| "model.language_model.layers.6.feed_forward.w1", |
| "model.language_model.layers.6.feed_forward.w2", |
| "model.language_model.layers.6.feed_forward.w3", |
| "model.language_model.layers.7.conv.in_proj", |
| "model.language_model.layers.7.conv.out_proj", |
| "model.language_model.layers.7.feed_forward.w1", |
| "model.language_model.layers.7.feed_forward.w2", |
| "model.language_model.layers.7.feed_forward.w3", |
| "model.language_model.layers.8.conv.in_proj", |
| "model.language_model.layers.8.conv.out_proj", |
| "model.language_model.layers.8.feed_forward.w1", |
| "model.language_model.layers.8.feed_forward.w2", |
| "model.language_model.layers.8.feed_forward.w3", |
| "model.language_model.layers.9.feed_forward.w1", |
| "model.language_model.layers.9.feed_forward.w2", |
| "model.language_model.layers.9.feed_forward.w3", |
| "model.language_model.layers.9.self_attn.k_proj", |
| "model.language_model.layers.9.self_attn.out_proj", |
| "model.language_model.layers.9.self_attn.q_proj", |
| "model.language_model.layers.9.self_attn.v_proj" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 256, |
| "num_bits": 4, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "group", |
| "symmetric": true, |
| "type": "int", |
| "zp_dtype": null |
| } |
| }, |
| "group_2": { |
| "format": "pack-quantized", |
| "input_activations": null, |
| "output_activations": null, |
| "targets": [ |
| "lm_head" |
| ], |
| "weights": { |
| "actorder": "static", |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 256, |
| "num_bits": 4, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "group", |
| "symmetric": true, |
| "type": "int", |
| "zp_dtype": null |
| } |
| } |
| }, |
| "format": "pack-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "model.multi_modal_projector.linear_1", |
| "model.multi_modal_projector.linear_2" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.17.1" |
| }, |
| "text_config": { |
| "_name_or_path": "LiquidAI/LFM2-2.6B", |
| "architectures": [ |
| "Lfm2ForCausalLM" |
| ], |
| "block_auto_adjust_ff_dim": false, |
| "block_dim": 2048, |
| "block_ffn_dim_multiplier": 1.0, |
| "block_mlp_init_scale": 1.0, |
| "block_multiple_of": 256, |
| "block_norm_eps": 1e-05, |
| "block_out_init_scale": 1.0, |
| "block_use_swiglu": true, |
| "block_use_xavier_init": true, |
| "bos_token_id": 1, |
| "conv_L_cache": 3, |
| "conv_bias": false, |
| "conv_dim": 2048, |
| "conv_dim_out": 2048, |
| "conv_use_xavier_init": true, |
| "dtype": "bfloat16", |
| "eos_token_id": 7, |
| "full_attn_idxs": null, |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 10752, |
| "layer_types": [ |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv" |
| ], |
| "max_position_embeddings": 128000, |
| "model_type": "lfm2", |
| "norm_eps": 1e-05, |
| "num_attention_heads": 32, |
| "num_heads": 32, |
| "num_hidden_layers": 30, |
| "num_key_value_heads": 8, |
| "pad_token_id": 0, |
| "rope_parameters": { |
| "rope_theta": 1000000.0, |
| "rope_type": "default" |
| }, |
| "theta": 1000000.0, |
| "tie_word_embeddings": true, |
| "use_cache": true, |
| "use_pos_enc": true, |
| "vocab_size": 65536 |
| }, |
| "tie_word_embeddings": false, |
| "tile_size": 512, |
| "transformers_version": "5.10.1", |
| "use_image_special_tokens": true, |
| "use_thumbnail": true, |
| "vision_config": { |
| "attention_dropout": 0.0, |
| "dtype": "bfloat16", |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "intermediate_size": 4304, |
| "layer_norm_eps": 1e-06, |
| "model_type": "siglip2_vision_model", |
| "num_attention_heads": 16, |
| "num_channels": 3, |
| "num_hidden_layers": 27, |
| "num_patches": 256, |
| "patch_size": 16, |
| "vision_use_head": false |
| } |
| } |
