KU-DFI/TelecomGPT-R1
32415
1{2 "architectures": [3 "Qwen3_5ForConditionalGeneration"4 ],5 "bos_token_id": null,6 "dtype": "float32",7 "eos_token_id": 248046,8 "image_token_id": 248056,9 "max_position_embeddings": 16384,10 "model_type": "qwen3_5",11 "pad_token_id": 248044,12 "text_config": {13 "attention_bias": false,14 "attention_dropout": 0.0,15 "attn_output_gate": true,16 "bos_token_id": null,17 "dtype": "float32",18 "eos_token_id": 248044,19 "full_attention_interval": 4,20 "head_dim": 256,21 "hidden_act": "silu",22 "hidden_size": 5120,23 "initializer_range": 0.02,24 "intermediate_size": 17408,25 "layer_types": [26 "linear_attention",27 "linear_attention",28 "linear_attention",29 "full_attention",30 "linear_attention",31 "linear_attention",32 "linear_attention",33 "full_attention",34 "linear_attention",35 "linear_attention",36 "linear_attention",37 "full_attention",38 "linear_attention",39 "linear_attention",40 "linear_attention",41 "full_attention",42 "linear_attention",43 "linear_attention",44 "linear_attention",45 "full_attention",46 "linear_attention",47 "linear_attention",48 "linear_attention",49 "full_attention",50 "linear_attention",51 "linear_attention",52 "linear_attention",53 "full_attention",54 "linear_attention",55 "linear_attention",56 "linear_attention",57 "full_attention",58 "linear_attention",59 "linear_attention",60 "linear_attention",61 "full_attention",62 "linear_attention",63 "linear_attention",64 "linear_attention",65 "full_attention",66 "linear_attention",67 "linear_attention",68 "linear_attention",69 "full_attention",70 "linear_attention",71 "linear_attention",72 "linear_attention",73 "full_attention",74 "linear_attention",75 "linear_attention",76 "linear_attention",77 "full_attention",78 "linear_attention",79 "linear_attention",80 "linear_attention",81 "full_attention",82 "linear_attention",83 "linear_attention",84 "linear_attention",85 "full_attention",86 "linear_attention",87 "linear_attention",88 "linear_attention",89 "full_attention"90 ],91 "linear_conv_kernel_dim": 4,92 "linear_key_head_dim": 128,93 "linear_num_key_heads": 16,94 "linear_num_value_heads": 48,95 "linear_value_head_dim": 128,96 "mamba_ssm_dtype": "float32",97 "max_position_embeddings": 262144,98 "mlp_only_layers": [],99 "model_type": "qwen3_5_text",100 "mtp_num_hidden_layers": 0,101 "mtp_use_dedicated_embeddings": false,102 "num_attention_heads": 24,103 "num_hidden_layers": 64,104 "num_key_value_heads": 4,105 "pad_token_id": null,106 "partial_rotary_factor": 0.25,107 "rms_norm_eps": 1e-06,108 "rope_parameters": {109 "mrope_interleaved": true,110 "mrope_section": [111 11,112 11,113 10114 ],115 "partial_rotary_factor": 0.25,116 "rope_theta": 10000000,117 "rope_type": "default"118 },119 "tie_word_embeddings": false,120 "use_cache": true,121 "vocab_size": 248320122 },123 "tie_word_embeddings": false,124 "transformers_version": "5.3.0.dev0",125 "video_token_id": 248057,126 "vision_config": {127 "deepstack_visual_indexes": [],128 "depth": 27,129 "dtype": "float32",130 "hidden_act": "gelu_pytorch_tanh",131 "hidden_size": 1152,132 "in_channels": 3,133 "initializer_range": 0.02,134 "intermediate_size": 4304,135 "model_type": "qwen3_5",136 "num_heads": 16,137 "num_position_embeddings": 2304,138 "out_hidden_size": 5120,139 "patch_size": 16,140 "spatial_merge_size": 2,141 "temporal_patch_size": 2142 },143 "vision_end_token_id": 248054,144 "vision_start_token_id": 248053145}146 