dots-studio/dots3-note-prev
278937
1{2 "architectures": [3 "Dots3NoteForCausalLM"4 ],5 "apply_mla_qkv_lora_rescale": true,6 "attention_bias": false,7 "attention_dropout": 0.0,8 "attention_gate_type": "headwise",9 "bos_token_id": 151643,10 "eos_token_id": 151668,11 "first_k_dense_replace": 1,12 "hidden_act": "silu",13 "hidden_size": 5120,14 "index_head_dim": 128,15 "index_n_heads": 64,16 "index_topk": 2048,17 "initializer_range": 0.02,18 "intermediate_size": 13824,19 "kv_lora_rank": 512,20 "layer_types": [21 "full_attention",22 "full_attention",23 "sliding_attention",24 "sliding_attention",25 "sliding_attention",26 "full_attention",27 "sliding_attention",28 "sliding_attention",29 "sliding_attention",30 "full_attention",31 "sliding_attention",32 "sliding_attention",33 "sliding_attention",34 "full_attention",35 "sliding_attention",36 "sliding_attention",37 "sliding_attention",38 "full_attention",39 "sliding_attention",40 "sliding_attention",41 "sliding_attention",42 "full_attention",43 "sliding_attention",44 "sliding_attention",45 "sliding_attention",46 "full_attention",47 "sliding_attention",48 "sliding_attention",49 "sliding_attention",50 "full_attention",51 "sliding_attention",52 "sliding_attention",53 "sliding_attention",54 "full_attention",55 "sliding_attention",56 "sliding_attention",57 "sliding_attention",58 "full_attention",59 "sliding_attention",60 "sliding_attention",61 "sliding_attention",62 "full_attention",63 "sliding_attention",64 "sliding_attention",65 "sliding_attention",66 "full_attention"67 ],68 "max_position_embeddings": 524288,69 "model_type": "dots3_note",70 "moe_intermediate_size": 1536,71 "moe_layer_freq": 1,72 "n_routed_experts": 256,73 "n_shared_experts": 1,74 "norm_topk_prob": true,75 "num_attention_heads": 128,76 "num_experts_per_tok": 8,77 "num_hidden_layers": 46,78 "num_key_value_heads": 128,79 "pretraining_tp": 1,80 "q_lora_rank": 1024,81 "qk_nope_head_dim": 128,82 "qk_rope_head_dim": 64,83 "rms_norm_eps": 1e-05,84 "rope_scaling": null,85 "rope_theta": 80000000.0,86 "routed_scaling_factor": 1.0,87 "scoring_func": "sigmoid",88 "sliding_window_size": 513,89 "swa_attention_gate_type": "headwise",90 "swa_kv_lora_rank": 1024,91 "swa_num_attention_heads": 64,92 "swa_num_key_value_heads": 64,93 "swa_q_lora_rank": 1024,94 "swa_qk_nope_head_dim": 192,95 "swa_qk_rope_head_dim": 64,96 "swa_rope_theta": 50000.0,97 "swa_v_head_dim": 128,98 "tie_word_embeddings": false,99 "topk_method": "noaux_tc",100 "torch_dtype": "bfloat16",101 "transformers_version": "4.36.0",102 "use_cache": true,103 "v_head_dim": 128,104 "vocab_size": 152064,105 "vision_config": {106 "embed_dim": 1536,107 "hidden_size": 5120,108 "intermediate_size": 4224,109 "moe_intermediate_size": 2112,110 "num_hidden_layers": 42,111 "num_attention_heads": 24,112 "num_channels": 3,113 "patch_size": 14,114 "spatial_merge_size": 2,115 "temporal_patch_size": 1,116 "rms_norm_eps": 1e-05,117 "use_bias": false,118 "use_qk_norm": true,119 "attn_implementation": "flash_attention_3",120 "initializer_range": 0.02,121 "is_causal": false,122 "post_norm": true,123 "pre_pixel_shuffle": true,124 "pyramid_num_routed": [125 -1,126 -1,127 -1,128 -1,129 -1,130 -1,131 -1,132 -1,133 -1,134 -1,135 -1,136 -1,137 -1,138 -1,139 -1,140 -1,141 -1,142 -1,143 -1,144 -1,145 -1,146 -1,147 -1,148 -1,149 -1,150 4,151 8,152 12,153 16,154 20,155 24,156 28,157 32,158 36,159 40,160 44,161 48,162 52,163 56,164 60,165 64,166 64167 ],168 "capacity_factor": 2,169 "router_scoring_func": "sigmoid",170 "router_scale": 1.0,171 "adapter_type": "patch_merger",172 "adapter_in_dim": 1536,173 "adapter_out_dim": 5120,174 "adapter_merge_size": 2175 },176 "audio_config": {177 "encoder_type": "dots",178 "whisper_config": {179 "d_model": 1280,180 "encoder_attention_heads": 20,181 "encoder_ffn_dim": 5120,182 "encoder_layers": 32,183 "num_mel_bins": 128,184 "max_source_positions": 6000,185 "activation_function": "swiglu"186 },187 "use_conv2d_stem": true,188 "use_rope": true,189 "use_rms_norm": true,190 "use_causal": false,191 "downsample_hidden_size": 480,192 "conv_chunksize": 500,193 "conv_stem_gradient_checkpointing": true,194 "conv_bucket_step": 10,195 "conv_bucket_max_elements": 20000,196 "rope_parameters": {197 "partial_rotary_factor": 0.5,198 "rope_theta": 10000.0199 },200 "merge_factor": 1,201 "chunk_seconds": 60,202 "whisper_adapter_in_dim": 1280,203 "whisper_adapter_out_dim": 5120,204 "sampling_rate": 16000,205 "audio_comp_start": "<|audio_comp_start|>",206 "audio_comp_span": "<|audio_comp_pad|>",207 "audio_comp_end": "<|audio_comp_end|>"208 }209}210 