| { |
| "architectures": [ |
| "Mistral3ForConditionalGeneration" |
| ], |
| "dtype": "bfloat16", |
| "image_token_index": 10, |
| "model_type": "mistral3", |
| "multimodal_projector_bias": false, |
| "projector_hidden_act": "gelu", |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": "nvfp4-pack-quantized", |
| "input_activations": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": "local", |
| "group_size": 16, |
| "num_bits": 4, |
| "observer": "static_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": "torch.float8_e4m3fn", |
| "strategy": "tensor_group", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| }, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 16, |
| "num_bits": 4, |
| "observer": "static_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": "torch.float8_e4m3fn", |
| "strategy": "tensor_group", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| } |
| } |
| }, |
| "format": "nvfp4-pack-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "model.vision_tower.transformer.layers.0.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.0.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.0.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.0.attention.k_proj", |
| "model.vision_tower.transformer.layers.0.attention.v_proj", |
| "model.vision_tower.transformer.layers.0.attention.q_proj", |
| "model.vision_tower.transformer.layers.0.attention.o_proj", |
| "model.vision_tower.transformer.layers.1.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.1.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.1.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.1.attention.k_proj", |
| "model.vision_tower.transformer.layers.1.attention.v_proj", |
| "model.vision_tower.transformer.layers.1.attention.q_proj", |
| "model.vision_tower.transformer.layers.1.attention.o_proj", |
| "model.vision_tower.transformer.layers.2.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.2.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.2.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.2.attention.k_proj", |
| "model.vision_tower.transformer.layers.2.attention.v_proj", |
| "model.vision_tower.transformer.layers.2.attention.q_proj", |
| "model.vision_tower.transformer.layers.2.attention.o_proj", |
| "model.vision_tower.transformer.layers.3.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.3.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.3.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.3.attention.k_proj", |
| "model.vision_tower.transformer.layers.3.attention.v_proj", |
| "model.vision_tower.transformer.layers.3.attention.q_proj", |
| "model.vision_tower.transformer.layers.3.attention.o_proj", |
| "model.vision_tower.transformer.layers.4.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.4.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.4.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.4.attention.k_proj", |
| "model.vision_tower.transformer.layers.4.attention.v_proj", |
| "model.vision_tower.transformer.layers.4.attention.q_proj", |
| "model.vision_tower.transformer.layers.4.attention.o_proj", |
| "model.vision_tower.transformer.layers.5.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.5.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.5.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.5.attention.k_proj", |
| "model.vision_tower.transformer.layers.5.attention.v_proj", |
| "model.vision_tower.transformer.layers.5.attention.q_proj", |
| "model.vision_tower.transformer.layers.5.attention.o_proj", |
| "model.vision_tower.transformer.layers.6.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.6.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.6.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.6.attention.k_proj", |
| "model.vision_tower.transformer.layers.6.attention.v_proj", |
| "model.vision_tower.transformer.layers.6.attention.q_proj", |
| "model.vision_tower.transformer.layers.6.attention.o_proj", |
| "model.vision_tower.transformer.layers.7.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.7.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.7.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.7.attention.k_proj", |
| "model.vision_tower.transformer.layers.7.attention.v_proj", |
| "model.vision_tower.transformer.layers.7.attention.q_proj", |
| "model.vision_tower.transformer.layers.7.attention.o_proj", |
| "model.vision_tower.transformer.layers.8.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.8.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.8.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.8.attention.k_proj", |
| "model.vision_tower.transformer.layers.8.attention.v_proj", |
| "model.vision_tower.transformer.layers.8.attention.q_proj", |
| "model.vision_tower.transformer.layers.8.attention.o_proj", |
| "model.vision_tower.transformer.layers.9.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.9.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.9.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.9.attention.k_proj", |
| "model.vision_tower.transformer.layers.9.attention.v_proj", |
| "model.vision_tower.transformer.layers.9.attention.q_proj", |
| "model.vision_tower.transformer.layers.9.attention.o_proj", |
| "model.vision_tower.transformer.layers.10.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.10.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.10.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.10.attention.k_proj", |
| "model.vision_tower.transformer.layers.10.attention.v_proj", |
| "model.vision_tower.transformer.layers.10.attention.q_proj", |
| "model.vision_tower.transformer.layers.10.attention.o_proj", |
| "model.vision_tower.transformer.layers.11.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.11.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.11.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.11.attention.k_proj", |
| "model.vision_tower.transformer.layers.11.attention.v_proj", |
| "model.vision_tower.transformer.layers.11.attention.q_proj", |
| "model.vision_tower.transformer.layers.11.attention.o_proj", |
| "model.vision_tower.transformer.layers.12.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.12.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.12.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.12.attention.k_proj", |
| "model.vision_tower.transformer.layers.12.attention.v_proj", |
| "model.vision_tower.transformer.layers.12.attention.q_proj", |
| "model.vision_tower.transformer.layers.12.attention.o_proj", |
| "model.vision_tower.transformer.layers.13.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.13.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.13.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.13.attention.k_proj", |
| "model.vision_tower.transformer.layers.13.attention.v_proj", |
| "model.vision_tower.transformer.layers.13.attention.q_proj", |
| "model.vision_tower.transformer.layers.13.attention.o_proj", |
| "model.vision_tower.transformer.layers.14.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.14.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.14.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.14.attention.k_proj", |
| "model.vision_tower.transformer.layers.14.attention.v_proj", |
| "model.vision_tower.transformer.layers.14.attention.q_proj", |
| "model.vision_tower.transformer.layers.14.attention.o_proj", |
| "model.vision_tower.transformer.layers.15.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.15.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.15.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.15.attention.k_proj", |
| "model.vision_tower.transformer.layers.15.attention.v_proj", |
| "model.vision_tower.transformer.layers.15.attention.q_proj", |
| "model.vision_tower.transformer.layers.15.attention.o_proj", |
| "model.vision_tower.transformer.layers.16.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.16.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.16.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.16.attention.k_proj", |
| "model.vision_tower.transformer.layers.16.attention.v_proj", |
| "model.vision_tower.transformer.layers.16.attention.q_proj", |
| "model.vision_tower.transformer.layers.16.attention.o_proj", |
| "model.vision_tower.transformer.layers.17.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.17.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.17.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.17.attention.k_proj", |
| "model.vision_tower.transformer.layers.17.attention.v_proj", |
| "model.vision_tower.transformer.layers.17.attention.q_proj", |
| "model.vision_tower.transformer.layers.17.attention.o_proj", |
| "model.vision_tower.transformer.layers.18.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.18.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.18.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.18.attention.k_proj", |
| "model.vision_tower.transformer.layers.18.attention.v_proj", |
| "model.vision_tower.transformer.layers.18.attention.q_proj", |
| "model.vision_tower.transformer.layers.18.attention.o_proj", |
| "model.vision_tower.transformer.layers.19.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.19.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.19.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.19.attention.k_proj", |
| "model.vision_tower.transformer.layers.19.attention.v_proj", |
| "model.vision_tower.transformer.layers.19.attention.q_proj", |
| "model.vision_tower.transformer.layers.19.attention.o_proj", |
| "model.vision_tower.transformer.layers.20.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.20.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.20.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.20.attention.k_proj", |
| "model.vision_tower.transformer.layers.20.attention.v_proj", |
| "model.vision_tower.transformer.layers.20.attention.q_proj", |
| "model.vision_tower.transformer.layers.20.attention.o_proj", |
| "model.vision_tower.transformer.layers.21.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.21.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.21.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.21.attention.k_proj", |
| "model.vision_tower.transformer.layers.21.attention.v_proj", |
| "model.vision_tower.transformer.layers.21.attention.q_proj", |
| "model.vision_tower.transformer.layers.21.attention.o_proj", |
| "model.vision_tower.transformer.layers.22.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.22.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.22.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.22.attention.k_proj", |
| "model.vision_tower.transformer.layers.22.attention.v_proj", |
| "model.vision_tower.transformer.layers.22.attention.q_proj", |
| "model.vision_tower.transformer.layers.22.attention.o_proj", |
| "model.vision_tower.transformer.layers.23.feed_forward.gate_proj", |
| "model.vision_tower.transformer.layers.23.feed_forward.up_proj", |
| "model.vision_tower.transformer.layers.23.feed_forward.down_proj", |
| "model.vision_tower.transformer.layers.23.attention.k_proj", |
| "model.vision_tower.transformer.layers.23.attention.v_proj", |
| "model.vision_tower.transformer.layers.23.attention.q_proj", |
| "model.vision_tower.transformer.layers.23.attention.o_proj", |
| "model.multi_modal_projector.patch_merger.merging_layer", |
| "model.multi_modal_projector.linear_1", |
| "model.multi_modal_projector.linear_2", |
| "model.language_model.layers.0.self_attn.q_proj", |
| "model.language_model.layers.0.self_attn.k_proj", |
| "model.language_model.layers.0.self_attn.v_proj", |
| "model.language_model.layers.0.self_attn.o_proj", |
| "model.language_model.layers.1.self_attn.q_proj", |
| "model.language_model.layers.1.self_attn.k_proj", |
| "model.language_model.layers.1.self_attn.v_proj", |
| "model.language_model.layers.1.self_attn.o_proj", |
| "model.language_model.layers.2.self_attn.q_proj", |
| "model.language_model.layers.2.self_attn.k_proj", |
| "model.language_model.layers.2.self_attn.v_proj", |
| "model.language_model.layers.2.self_attn.o_proj", |
| "model.language_model.layers.3.self_attn.q_proj", |
| "model.language_model.layers.3.self_attn.k_proj", |
| "model.language_model.layers.3.self_attn.v_proj", |
| "model.language_model.layers.3.self_attn.o_proj", |
| "model.language_model.layers.4.self_attn.q_proj", |
| "model.language_model.layers.4.self_attn.k_proj", |
| "model.language_model.layers.4.self_attn.v_proj", |
| "model.language_model.layers.4.self_attn.o_proj", |
| "model.language_model.layers.5.self_attn.q_proj", |
| "model.language_model.layers.5.self_attn.k_proj", |
| "model.language_model.layers.5.self_attn.v_proj", |
| "model.language_model.layers.5.self_attn.o_proj", |
| "model.language_model.layers.6.self_attn.q_proj", |
| "model.language_model.layers.6.self_attn.k_proj", |
| "model.language_model.layers.6.self_attn.v_proj", |
| "model.language_model.layers.6.self_attn.o_proj", |
| "model.language_model.layers.7.self_attn.q_proj", |
| "model.language_model.layers.7.self_attn.k_proj", |
| "model.language_model.layers.7.self_attn.v_proj", |
| "model.language_model.layers.7.self_attn.o_proj", |
| "model.language_model.layers.8.self_attn.q_proj", |
| "model.language_model.layers.8.self_attn.k_proj", |
| "model.language_model.layers.8.self_attn.v_proj", |
| "model.language_model.layers.8.self_attn.o_proj", |
| "model.language_model.layers.9.self_attn.q_proj", |
| "model.language_model.layers.9.self_attn.k_proj", |
| "model.language_model.layers.9.self_attn.v_proj", |
| "model.language_model.layers.9.self_attn.o_proj", |
| "model.language_model.layers.10.self_attn.q_proj", |
| "model.language_model.layers.10.self_attn.k_proj", |
| "model.language_model.layers.10.self_attn.v_proj", |
| "model.language_model.layers.10.self_attn.o_proj", |
| "model.language_model.layers.11.self_attn.q_proj", |
| "model.language_model.layers.11.self_attn.k_proj", |
| "model.language_model.layers.11.self_attn.v_proj", |
| "model.language_model.layers.11.self_attn.o_proj", |
| "model.language_model.layers.12.self_attn.q_proj", |
| "model.language_model.layers.12.self_attn.k_proj", |
| "model.language_model.layers.12.self_attn.v_proj", |
| "model.language_model.layers.12.self_attn.o_proj", |
| "model.language_model.layers.13.self_attn.q_proj", |
| "model.language_model.layers.13.self_attn.k_proj", |
| "model.language_model.layers.13.self_attn.v_proj", |
| "model.language_model.layers.13.self_attn.o_proj", |
| "model.language_model.layers.14.self_attn.q_proj", |
| "model.language_model.layers.14.self_attn.k_proj", |
| "model.language_model.layers.14.self_attn.v_proj", |
| "model.language_model.layers.14.self_attn.o_proj", |
| "model.language_model.layers.15.self_attn.q_proj", |
| "model.language_model.layers.15.self_attn.k_proj", |
| "model.language_model.layers.15.self_attn.v_proj", |
| "model.language_model.layers.15.self_attn.o_proj", |
| "model.language_model.layers.16.self_attn.q_proj", |
| "model.language_model.layers.16.self_attn.k_proj", |
| "model.language_model.layers.16.self_attn.v_proj", |
| "model.language_model.layers.16.self_attn.o_proj", |
| "model.language_model.layers.17.self_attn.q_proj", |
| "model.language_model.layers.17.self_attn.k_proj", |
| "model.language_model.layers.17.self_attn.v_proj", |
| "model.language_model.layers.17.self_attn.o_proj", |
| "model.language_model.layers.18.self_attn.q_proj", |
| "model.language_model.layers.18.self_attn.k_proj", |
| "model.language_model.layers.18.self_attn.v_proj", |
| "model.language_model.layers.18.self_attn.o_proj", |
| "model.language_model.layers.19.self_attn.q_proj", |
| "model.language_model.layers.19.self_attn.k_proj", |
| "model.language_model.layers.19.self_attn.v_proj", |
| "model.language_model.layers.19.self_attn.o_proj", |
| "model.language_model.layers.20.self_attn.q_proj", |
| "model.language_model.layers.20.self_attn.k_proj", |
| "model.language_model.layers.20.self_attn.v_proj", |
| "model.language_model.layers.20.self_attn.o_proj", |
| "model.language_model.layers.21.self_attn.q_proj", |
| "model.language_model.layers.21.self_attn.k_proj", |
| "model.language_model.layers.21.self_attn.v_proj", |
| "model.language_model.layers.21.self_attn.o_proj", |
| "model.language_model.layers.22.self_attn.q_proj", |
| "model.language_model.layers.22.self_attn.k_proj", |
| "model.language_model.layers.22.self_attn.v_proj", |
| "model.language_model.layers.22.self_attn.o_proj", |
| "model.language_model.layers.23.self_attn.q_proj", |
| "model.language_model.layers.23.self_attn.k_proj", |
| "model.language_model.layers.23.self_attn.v_proj", |
| "model.language_model.layers.23.self_attn.o_proj", |
| "model.language_model.layers.24.self_attn.q_proj", |
| "model.language_model.layers.24.self_attn.k_proj", |
| "model.language_model.layers.24.self_attn.v_proj", |
| "model.language_model.layers.24.self_attn.o_proj", |
| "model.language_model.layers.25.self_attn.q_proj", |
| "model.language_model.layers.25.self_attn.k_proj", |
| "model.language_model.layers.25.self_attn.v_proj", |
| "model.language_model.layers.25.self_attn.o_proj", |
| "model.language_model.layers.26.self_attn.q_proj", |
| "model.language_model.layers.26.self_attn.k_proj", |
| "model.language_model.layers.26.self_attn.v_proj", |
| "model.language_model.layers.26.self_attn.o_proj", |
| "model.language_model.layers.27.self_attn.q_proj", |
| "model.language_model.layers.27.self_attn.k_proj", |
| "model.language_model.layers.27.self_attn.v_proj", |
| "model.language_model.layers.27.self_attn.o_proj", |
| "model.language_model.layers.28.self_attn.q_proj", |
| "model.language_model.layers.28.self_attn.k_proj", |
| "model.language_model.layers.28.self_attn.v_proj", |
| "model.language_model.layers.28.self_attn.o_proj", |
| "model.language_model.layers.29.self_attn.q_proj", |
| "model.language_model.layers.29.self_attn.k_proj", |
| "model.language_model.layers.29.self_attn.v_proj", |
| "model.language_model.layers.29.self_attn.o_proj", |
| "model.language_model.layers.30.self_attn.q_proj", |
| "model.language_model.layers.30.self_attn.k_proj", |
| "model.language_model.layers.30.self_attn.v_proj", |
| "model.language_model.layers.30.self_attn.o_proj", |
| "model.language_model.layers.31.self_attn.q_proj", |
| "model.language_model.layers.31.self_attn.k_proj", |
| "model.language_model.layers.31.self_attn.v_proj", |
| "model.language_model.layers.31.self_attn.o_proj", |
| "model.language_model.layers.32.self_attn.q_proj", |
| "model.language_model.layers.32.self_attn.k_proj", |
| "model.language_model.layers.32.self_attn.v_proj", |
| "model.language_model.layers.32.self_attn.o_proj", |
| "model.language_model.layers.33.self_attn.q_proj", |
| "model.language_model.layers.33.self_attn.k_proj", |
| "model.language_model.layers.33.self_attn.v_proj", |
| "model.language_model.layers.33.self_attn.o_proj", |
| "model.language_model.layers.34.self_attn.q_proj", |
| "model.language_model.layers.34.self_attn.k_proj", |
| "model.language_model.layers.34.self_attn.v_proj", |
| "model.language_model.layers.34.self_attn.o_proj", |
| "model.language_model.layers.35.self_attn.q_proj", |
| "model.language_model.layers.35.self_attn.k_proj", |
| "model.language_model.layers.35.self_attn.v_proj", |
| "model.language_model.layers.35.self_attn.o_proj", |
| "model.language_model.layers.36.self_attn.q_proj", |
| "model.language_model.layers.36.self_attn.k_proj", |
| "model.language_model.layers.36.self_attn.v_proj", |
| "model.language_model.layers.36.self_attn.o_proj", |
| "model.language_model.layers.37.self_attn.q_proj", |
| "model.language_model.layers.37.self_attn.k_proj", |
| "model.language_model.layers.37.self_attn.v_proj", |
| "model.language_model.layers.37.self_attn.o_proj", |
| "model.language_model.layers.38.self_attn.q_proj", |
| "model.language_model.layers.38.self_attn.k_proj", |
| "model.language_model.layers.38.self_attn.v_proj", |
| "model.language_model.layers.38.self_attn.o_proj", |
| "model.language_model.layers.39.self_attn.q_proj", |
| "model.language_model.layers.39.self_attn.k_proj", |
| "model.language_model.layers.39.self_attn.v_proj", |
| "model.language_model.layers.39.self_attn.o_proj", |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.13.1.dev4+gb055afc" |
| }, |
| "spatial_merge_size": 2, |
| "text_config": { |
| "attention_dropout": 0.0, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 16384, |
| "max_position_embeddings": 262144, |
| "model_type": "ministral3", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 8, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "beta_fast": 32.0, |
| "beta_slow": 1.0, |
| "factor": 16.0, |
| "llama_4_scaling_beta": 0.1, |
| "mscale": 1.0, |
| "mscale_all_dim": 1.0, |
| "original_max_position_embeddings": 16384, |
| "rope_theta": 1000000000.0, |
| "rope_type": "yarn", |
| "type": "yarn" |
| }, |
| "sliding_window": null, |
| "use_cache": true, |
| "vocab_size": 131072 |
| }, |
| "transformers_version": "5.0.0rc1", |
| "vision_config": { |
| "attention_dropout": 0.0, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 1024, |
| "image_size": 1540, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "model_type": "pixtral", |
| "num_attention_heads": 16, |
| "num_channels": 3, |
| "num_hidden_layers": 24, |
| "patch_size": 14, |
| "rope_parameters": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| } |
| }, |
| "vision_feature_layer": -1 |
| } |
