andrewor14's picture
Upload Gemma3ForConditionalGeneration
8c15c04 verified
{
"architectures": [
"Gemma3ForConditionalGeneration"
],
"boi_token_index": 255999,
"bos_token_id": 2,
"dtype": "bfloat16",
"eoi_token_index": 256000,
"eos_token_id": 106,
"image_token_index": 262144,
"initializer_range": 0.02,
"mm_tokens_per_image": 256,
"model_type": "gemma3",
"pad_token_id": 0,
"quantization_config": {
"include_input_output_embeddings": false,
"modules_to_not_convert": null,
"quant_method": "torchao",
"quant_type": {
"default": {
"_data": {
"group_size": 128,
"int4_choose_qparams_algorithm": {
"_data": "TINYGEMM",
"_type": "Int4ChooseQParamsAlgorithm"
},
"int4_packing_format": {
"_data": "PLAIN",
"_type": "Int4PackingFormat"
},
"layout": {
"_data": {
"inner_k_tiles": 8
},
"_type": "TensorCoreTiledLayout",
"_version": 1
},
"preserve_zero": null,
"set_inductor_config": true,
"use_hqq": false,
"zero_point_domain": {
"_data": "NONE",
"_type": "ZeroPointDomain"
}
},
"_type": "Int4WeightOnlyConfig",
"_version": 2
}
},
"quant_type_kwargs": {},
"untie_embedding_weights": false
},
"text_config": {
"_sliding_window_pattern": 6,
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"cache_implementation": "hybrid",
"dtype": "bfloat16",
"final_logit_softcapping": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 3840,
"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": "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,
"use_cache": true,
"vocab_size": 262208
},
"transformers_version": "4.56.2",
"unsloth_fixed": true,
"unsloth_version": "2025.9.11",
"vision_config": {
"attention_dropout": 0.0,
"dtype": "bfloat16",
"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,
"vision_use_head": false
}
}