| { |
| "architectures": [ |
| "Gemma4ForConditionalGeneration" |
| ], |
| "audio_config": null, |
| "audio_token_id": 258881, |
| "boa_token_id": 256000, |
| "boi_token_id": 255999, |
| "dtype": "bfloat16", |
| "eoa_token_id": 258883, |
| "eoa_token_index": 258883, |
| "eoi_token_id": 258882, |
| "eos_token_id": [ |
| 1, |
| 106 |
| ], |
| "image_token_id": 258880, |
| "initializer_range": 0.02, |
| "model_type": "gemma4", |
| "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": "memoryless_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.language_model.layers.0.router.proj", |
| "model.language_model.layers.1.router.proj", |
| "model.language_model.layers.2.router.proj", |
| "model.language_model.layers.3.router.proj", |
| "model.language_model.layers.4.router.proj", |
| "model.language_model.layers.5.router.proj", |
| "model.language_model.layers.6.router.proj", |
| "model.language_model.layers.7.router.proj", |
| "model.language_model.layers.8.router.proj", |
| "model.language_model.layers.9.router.proj", |
| "model.language_model.layers.10.router.proj", |
| "model.language_model.layers.11.router.proj", |
| "model.language_model.layers.12.router.proj", |
| "model.language_model.layers.13.router.proj", |
| "model.language_model.layers.14.router.proj", |
| "model.language_model.layers.15.router.proj", |
| "model.language_model.layers.16.router.proj", |
| "model.language_model.layers.17.router.proj", |
| "model.language_model.layers.18.router.proj", |
| "model.language_model.layers.19.router.proj", |
| "model.language_model.layers.20.router.proj", |
| "model.language_model.layers.21.router.proj", |
| "model.language_model.layers.22.router.proj", |
| "model.language_model.layers.23.router.proj", |
| "model.language_model.layers.24.router.proj", |
| "model.language_model.layers.25.router.proj", |
| "model.language_model.layers.26.router.proj", |
| "model.language_model.layers.27.router.proj", |
| "model.language_model.layers.28.router.proj", |
| "model.language_model.layers.29.router.proj", |
| "model.vision_tower.patch_embedder.input_proj", |
| "model.vision_tower.encoder.layers.0.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.0.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.0.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.0.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.0.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.0.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.0.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.1.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.1.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.1.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.2.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.2.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.2.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.3.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.3.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.3.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.3.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.3.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.3.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.3.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.4.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.4.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.4.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.4.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.4.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.4.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.4.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.5.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.5.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.5.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.6.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.6.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.6.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.7.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.7.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.7.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.7.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.7.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.7.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.7.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.8.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.8.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.8.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.8.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.8.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.8.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.8.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.9.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.9.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.9.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.9.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.9.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.9.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.9.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.10.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.10.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.10.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.10.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.10.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.10.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.10.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.11.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.11.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.11.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.12.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.12.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.12.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.13.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.13.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.13.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.14.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.14.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.14.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.15.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.15.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.15.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.16.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.16.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.16.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.17.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.17.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.17.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.17.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.17.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.17.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.17.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.18.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.18.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.18.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.18.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.18.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.18.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.18.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.19.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.19.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.19.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.20.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.20.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.20.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.20.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.20.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.20.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.20.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.21.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.21.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.21.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.22.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.22.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.22.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.23.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.23.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.23.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.24.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.24.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.24.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.24.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.24.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.24.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.24.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.25.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.25.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.25.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.26.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.26.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.26.mlp.down_proj.linear", |
| "model.embed_vision.embedding_projection", |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.15.1.a20260409" |
| }, |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attention_k_eq_v": true, |
| "bos_token_id": 2, |
| "dtype": "bfloat16", |
| "enable_moe_block": true, |
| "eos_token_id": 1, |
| "final_logit_softcapping": 30.0, |
| "global_head_dim": 512, |
| "head_dim": 256, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 2816, |
| "hidden_size_per_layer_input": 0, |
| "initializer_range": 0.02, |
| "intermediate_size": 2112, |
| "layer_types": [ |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 262144, |
| "model_type": "gemma4_text", |
| "moe_intermediate_size": 704, |
| "num_attention_heads": 16, |
| "num_experts": 128, |
| "num_global_key_value_heads": 2, |
| "num_hidden_layers": 30, |
| "num_key_value_heads": 8, |
| "num_kv_shared_layers": 0, |
| "pad_token_id": 0, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "full_attention": { |
| "partial_rotary_factor": 0.25, |
| "rope_theta": 1000000.0, |
| "rope_type": "proportional" |
| }, |
| "sliding_attention": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| } |
| }, |
| "sliding_window": 1024, |
| "tie_word_embeddings": true, |
| "top_k_experts": 8, |
| "use_bidirectional_attention": "vision", |
| "use_cache": true, |
| "use_double_wide_mlp": false, |
| "vocab_size": 262144, |
| "vocab_size_per_layer_input": 262144 |
| }, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.5.4", |
| "video_token_id": 258884, |
| "vision_config": { |
| "_name_or_path": "", |
| "architectures": null, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "chunk_size_feed_forward": 0, |
| "default_output_length": 280, |
| "dtype": "bfloat16", |
| "global_head_dim": 72, |
| "head_dim": 72, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 4304, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "max_position_embeddings": 131072, |
| "model_type": "gemma4_vision", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 27, |
| "num_key_value_heads": 16, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "patch_size": 16, |
| "pooling_kernel_size": 3, |
| "position_embedding_size": 10240, |
| "problem_type": null, |
| "return_dict": true, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "rope_theta": 100.0, |
| "rope_type": "default" |
| }, |
| "standardize": true, |
| "use_clipped_linears": false |
| }, |
| "vision_soft_tokens_per_image": 280 |
| } |
