cmcmaster/transcript-to-note
031
1{2 "architectures": [3 "Gemma3ForConditionalGeneration"4 ],5 "boi_token_index": 255999,6 "bos_token_id": 2,7 "dtype": "float32",8 "eoi_token_index": 256000,9 "eos_token_id": 1,10 "image_token_index": 262144,11 "initializer_range": 0.02,12 "mm_tokens_per_image": 256,13 "model_type": "gemma3",14 "pad_token_id": 0,15 "text_config": {16 "_sliding_window_pattern": 6,17 "attention_bias": false,18 "attention_dropout": 0.0,19 "attn_logit_softcapping": null,20 "dtype": "float32",21 "final_logit_softcapping": null,22 "head_dim": 256,23 "hidden_activation": "gelu_pytorch_tanh",24 "hidden_size": 2560,25 "initializer_range": 0.02,26 "intermediate_size": 10240,27 "layer_types": [28 "sliding_attention",29 "sliding_attention",30 "sliding_attention",31 "sliding_attention",32 "sliding_attention",33 "full_attention",34 "sliding_attention",35 "sliding_attention",36 "sliding_attention",37 "sliding_attention",38 "sliding_attention",39 "full_attention",40 "sliding_attention",41 "sliding_attention",42 "sliding_attention",43 "sliding_attention",44 "sliding_attention",45 "full_attention",46 "sliding_attention",47 "sliding_attention",48 "sliding_attention",49 "sliding_attention",50 "sliding_attention",51 "full_attention",52 "sliding_attention",53 "sliding_attention",54 "sliding_attention",55 "sliding_attention",56 "sliding_attention",57 "full_attention",58 "sliding_attention",59 "sliding_attention",60 "sliding_attention",61 "sliding_attention"62 ],63 "max_position_embeddings": 131072,64 "model_type": "gemma3_text",65 "num_attention_heads": 8,66 "num_hidden_layers": 34,67 "num_key_value_heads": 4,68 "query_pre_attn_scalar": 256,69 "rms_norm_eps": 1e-06,70 "rope_local_base_freq": 10000,71 "rope_scaling": {72 "factor": 8.0,73 "rope_type": "linear"74 },75 "rope_theta": 1000000,76 "sliding_window": 1024,77 "use_bidirectional_attention": false,78 "use_cache": true,79 "vocab_size": 26220880 },81 "transformers_version": "4.57.6",82 "vision_config": {83 "attention_dropout": 0.0,84 "dtype": "float32",85 "hidden_act": "gelu_pytorch_tanh",86 "hidden_size": 1152,87 "image_size": 896,88 "intermediate_size": 4304,89 "layer_norm_eps": 1e-06,90 "model_type": "siglip_vision_model",91 "num_attention_heads": 16,92 "num_channels": 3,93 "num_hidden_layers": 27,94 "patch_size": 14,95 "vision_use_head": false96 }97}98 