Buckets:
| { | |
| "architectures": [ | |
| "Gemma4UnifiedForConditionalGeneration" | |
| ], | |
| "audio_config": { | |
| "_name_or_path": "", | |
| "architectures": null, | |
| "audio_embed_dim": 640, | |
| "audio_samples_per_token": 640, | |
| "chunk_size_feed_forward": 0, | |
| "dtype": null, | |
| "hidden_size": 640, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "model_type": "gemma4_unified_audio", | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_proj_dims": 640, | |
| "problem_type": null, | |
| "return_dict": true, | |
| "rms_norm_eps": 1e-06 | |
| }, | |
| "audio_token_id": 258881, | |
| "boa_token_id": 256000, | |
| "boi_token_id": 255999, | |
| "dtype": "bfloat16", | |
| "eoa_token_index": 258883, | |
| "eoi_token_id": 258882, | |
| "eos_token_id": [ | |
| 1, | |
| 106 | |
| ], | |
| "image_token_id": 258880, | |
| "initializer_range": 0.02, | |
| "model_type": "gemma4_unified", | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_k_eq_v": true, | |
| "bos_token_id": 2, | |
| "enable_moe_block": false, | |
| "eos_token_id": 1, | |
| "final_logit_softcapping": 30.0, | |
| "global_head_dim": 512, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 3840, | |
| "hidden_size_per_layer_input": 0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 15360, | |
| "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", | |
| "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": 131072, | |
| "model_type": "gemma4_unified_text", | |
| "moe_intermediate_size": null, | |
| "num_attention_heads": 16, | |
| "num_experts": null, | |
| "num_global_key_value_heads": 1, | |
| "num_hidden_layers": 48, | |
| "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": null, | |
| "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": "5.10.0.dev0", | |
| "video_token_id": 258884, | |
| "vision_config": { | |
| "_name_or_path": "", | |
| "architectures": null, | |
| "chunk_size_feed_forward": 0, | |
| "dtype": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "mm_embed_dim": 3840, | |
| "mm_posemb_size": 1120, | |
| "model_patch_size": 48, | |
| "model_type": "gemma4_unified_vision", | |
| "num_soft_tokens": 280, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_proj_dims": 3840, | |
| "patch_size": 16, | |
| "pooling_kernel_size": 3, | |
| "problem_type": null, | |
| "return_dict": true, | |
| "rms_norm_eps": 1e-06 | |
| }, | |
| "weight_format": "jang_affine", | |
| "quantization": { | |
| "group_size": 32, | |
| "bits": 8, | |
| "mode": "affine", | |
| "tied_embedding": "fp16_passthrough", | |
| "language_model.model.layers.0.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.down_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.gate_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.up_proj": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine" | |
| } | |
| }, | |
| "capabilities": { | |
| "reasoning_parser": "gemma4", | |
| "tool_parser": "gemma4", | |
| "think_in_template": false, | |
| "supports_tools": true, | |
| "supports_thinking": true, | |
| "family": "gemma4", | |
| "modality": "vision", | |
| "cache_type": "kv" | |
| } | |
| } |
Xet Storage Details
- Size:
- 22.7 kB
- Xet hash:
- 364401a046a3e267f37a3699e9f4d886fc7298dffba82042f501f3e00c464fd7
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.