| { | |
| "architectures": [ | |
| "Gemma3ForConditionalGeneration" | |
| ], | |
| "boi_token_index": 255999, | |
| "bos_token_id": 2, | |
| "eoi_token_index": 256000, | |
| "eos_token_id": 106, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2", | |
| "3": "LABEL_3", | |
| "4": "LABEL_4", | |
| "5": "LABEL_5", | |
| "6": "LABEL_6", | |
| "7": "LABEL_7", | |
| "8": "LABEL_8", | |
| "9": "LABEL_9", | |
| "10": "LABEL_10", | |
| "11": "LABEL_11", | |
| "12": "LABEL_12", | |
| "13": "LABEL_13", | |
| "14": "LABEL_14", | |
| "15": "LABEL_15", | |
| "16": "LABEL_16" | |
| }, | |
| "image_token_index": 262144, | |
| "initializer_range": 0.02, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_10": 10, | |
| "LABEL_11": 11, | |
| "LABEL_12": 12, | |
| "LABEL_13": 13, | |
| "LABEL_14": 14, | |
| "LABEL_15": 15, | |
| "LABEL_16": 16, | |
| "LABEL_2": 2, | |
| "LABEL_3": 3, | |
| "LABEL_4": 4, | |
| "LABEL_5": 5, | |
| "LABEL_6": 6, | |
| "LABEL_7": 7, | |
| "LABEL_8": 8, | |
| "LABEL_9": 9 | |
| }, | |
| "mm_tokens_per_image": 256, | |
| "model_type": "gemma3", | |
| "pad_token_id": 0, | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "bfloat16", | |
| "bnb_4bit_quant_storage": "uint8", | |
| "bnb_4bit_quant_type": "nf4", | |
| "bnb_4bit_use_double_quant": true, | |
| "llm_int8_enable_fp32_cpu_offload": false, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": [ | |
| "lm_head", | |
| "multi_modal_projector", | |
| "merger", | |
| "modality_projection", | |
| "language_model.model.layers.14.mlp", | |
| "language_model.model.layers.2.self_attn", | |
| "language_model.model.layers.12.mlp", | |
| "language_model.model.layers.8.self_attn", | |
| "language_model.model.layers.6.self_attn", | |
| "language_model.model.layers.13.mlp", | |
| "language_model.model.layers.1.mlp", | |
| "language_model.model.layers.10.mlp", | |
| "language_model.model.layers.16.mlp", | |
| "language_model.model.layers.5.self_attn", | |
| "language_model.model.layers.2.mlp", | |
| "language_model.model.layers.4.mlp", | |
| "language_model.model.layers.5.mlp", | |
| "language_model.model.layers.9.mlp", | |
| "language_model.model.layers.7.self_attn", | |
| "language_model.model.layers.6.mlp", | |
| "language_model.model.layers.8.mlp", | |
| "vision_tower.vision_model.encoder.layers.23.self_attn", | |
| "language_model.model.layers.7.mlp", | |
| "language_model.model.layers.3.self_attn", | |
| "language_model.model.layers.11.mlp", | |
| "language_model.model.layers.3.mlp", | |
| "vision_tower.vision_model.encoder.layers.19.self_attn", | |
| "vision_tower.vision_model.encoder.layers.25.self_attn", | |
| "vision_tower.vision_model.encoder.layers.22.self_attn", | |
| "vision_tower.vision_model.encoder.layers.21.self_attn", | |
| "vision_tower.vision_model.encoder.layers.18.self_attn", | |
| "vision_tower.vision_model.encoder.layers.17.mlp", | |
| "vision_tower.vision_model.encoder.layers.24.self_attn", | |
| "vision_tower.vision_model.encoder.layers.24.mlp", | |
| "vision_tower.vision_model.encoder.layers.26.self_attn", | |
| "vision_tower.vision_model.encoder.layers.20.mlp", | |
| "vision_tower.vision_model.encoder.layers.20.self_attn", | |
| "vision_tower.vision_model.encoder.layers.23.mlp", | |
| "vision_tower.vision_model.encoder.layers.19.mlp", | |
| "vision_tower.vision_model.encoder.layers.15.self_attn", | |
| "vision_tower.vision_model.encoder.layers.14.mlp", | |
| "vision_tower.vision_model.encoder.layers.13.mlp", | |
| "vision_tower.vision_model.encoder.layers.21.mlp", | |
| "vision_tower.vision_model.encoder.layers.16.mlp", | |
| "vision_tower.vision_model.encoder.layers.25.mlp", | |
| "vision_tower.vision_model.encoder.layers.15.mlp", | |
| "vision_tower.vision_model.encoder.layers.14.self_attn", | |
| "vision_tower.vision_model.encoder.layers.16.self_attn", | |
| "vision_tower.vision_model.encoder.layers.10.mlp", | |
| "vision_tower.vision_model.encoder.layers.17.self_attn", | |
| "vision_tower.vision_model.encoder.layers.9.mlp", | |
| "vision_tower.vision_model.encoder.layers.11.mlp", | |
| "vision_tower.vision_model.encoder.layers.12.mlp", | |
| "vision_tower.vision_model.encoder.layers.10.self_attn", | |
| "vision_tower.vision_model.encoder.layers.22.mlp", | |
| "vision_tower.vision_model.encoder.layers.13.self_attn", | |
| "vision_tower.vision_model.encoder.layers.18.mlp", | |
| "vision_tower.vision_model.encoder.layers.12.self_attn", | |
| "vision_tower.vision_model.encoder.layers.7.mlp", | |
| "vision_tower.vision_model.encoder.layers.6.mlp", | |
| "vision_tower.vision_model.encoder.layers.8.self_attn", | |
| "vision_tower.vision_model.encoder.layers.9.self_attn", | |
| "vision_tower.vision_model.encoder.layers.4.mlp", | |
| "vision_tower.vision_model.encoder.layers.5.mlp", | |
| "vision_tower.vision_model.encoder.layers.8.mlp", | |
| "vision_tower.vision_model.encoder.layers.1.mlp", | |
| "vision_tower.vision_model.encoder.layers.6.self_attn", | |
| "vision_tower.vision_model.encoder.layers.4.self_attn", | |
| "vision_tower.vision_model.encoder.layers.11.self_attn", | |
| "vision_tower.vision_model.encoder.layers.7.self_attn", | |
| "vision_tower.vision_model.encoder.layers.0.self_attn", | |
| "vision_tower.vision_model.encoder.layers.3.mlp", | |
| "vision_tower.vision_model.encoder.layers.1.self_attn", | |
| "vision_tower.vision_model.encoder.layers.2.mlp", | |
| "vision_tower.vision_model.encoder.layers.5.self_attn", | |
| "vision_tower.vision_model.encoder.layers.3.self_attn", | |
| "vision_tower.vision_model.encoder.layers.0.mlp", | |
| "vision_tower.vision_model.encoder.layers.26.mlp", | |
| "vision_tower.vision_model.encoder.layers.2.self_attn" | |
| ], | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "cache_implementation": "hybrid", | |
| "final_logit_softcapping": null, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 3840, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 15360, | |
| "max_position_embeddings": 131072, | |
| "model_type": "gemma3_text", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 8, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_local_base_freq": 10000.0, | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "rope_type": "linear" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 1024, | |
| "sliding_window_pattern": 6, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "vocab_size": 262208 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.50.0", | |
| "unsloth_fixed": true, | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_size": 896, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "patch_size": 14, | |
| "torch_dtype": "bfloat16", | |
| "vision_use_head": false | |
| } | |
| } | |