Pilot-4B-v1.5 / config.json
michaelvu1207's picture
Pilot-4B v1.5: weights, driver, inference example, model card
042382e verified
Raw History Blame Contribute Delete
6.09 kB
{
"_name_or_path": "",
"architectures": [
"QwenDriveForPlanning"
],
"chunk_size_feed_forward": 0,
"current_image_pixels": 921600,
"dtype": "bfloat16",
"expert_config": {
"_name_or_path": "",
"architectures": null,
"chunk_size_feed_forward": 0,
"dtype": null,
"ego_status_dim": 8,
"fourier_max_frequency": 16.0,
"fourier_num_features": 16,
"head_dim": 256,
"hidden_size": 1024,
"history_dynamics_dim": 2,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"intermediate_size": 3584,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layers_per_kv": 4,
"model_type": "qwen_drive_planning_expert",
"mrope_section": [
11,
11,
10
],
"nav_command_classes": 3,
"num_attention_heads": 16,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"output_attentions": false,
"output_hidden_states": false,
"partial_rotary_factor": 0.25,
"problem_type": null,
"return_dict": true,
"rms_norm_eps": 1e-05,
"rope_theta": 10000000.0,
"time_embed_dim": 128,
"time_embed_scale": 1000.0
},
"history_image_pixels": 174080,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_patch_size": 16,
"image_spatial_merge_size": 2,
"image_temporal_patch_size": 2,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"max_reasoning_tokens": 256,
"min_one_minus_t": 0.1,
"model_type": "qwen_drive",
"noise_init_std": 1.0,
"noise_seed": 42,
"num_future_points": 50,
"num_history_points": 16,
"num_inference_steps": 10,
"output_attentions": false,
"output_hidden_states": false,
"problem_type": null,
"return_dict": true,
"trajectory_hz": 10.0,
"trajectory_point_dim": 3,
"trajectory_scale": [
165.0,
25.0,
1.5703125
],
"transformers_version": "5.15.0",
"vlm_config": {
"_name_or_path": "",
"architectures": [
"Qwen3_5ForConditionalGeneration"
],
"chunk_size_feed_forward": 0,
"dtype": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_token_id": 248056,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"model_type": "qwen3_5",
"output_attentions": false,
"output_hidden_states": false,
"problem_type": null,
"return_dict": true,
"text_config": {
"_name_or_path": "",
"architectures": null,
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 2560,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 9216,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_types": [
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention"
],
"linear_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 32,
"linear_value_head_dim": 128,
"mamba_ssm_dtype": "float32",
"max_position_embeddings": 32768,
"mlp_only_layers": [],
"model_type": "qwen3_5_text",
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"num_attention_heads": 16,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": null,
"partial_rotary_factor": 0.25,
"problem_type": null,
"return_dict": true,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"partial_rotary_factor": 0.25,
"rope_theta": 10000000,
"rope_type": "default"
},
"tie_word_embeddings": true,
"use_cache": true,
"vocab_size": 248320
},
"tie_word_embeddings": true,
"video_token_id": 248057,
"vision_config": {
"_name_or_path": "",
"architectures": null,
"chunk_size_feed_forward": 0,
"deepstack_visual_indexes": [],
"depth": 24,
"dtype": null,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 4096,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"model_type": "qwen3_5_vision",
"num_heads": 16,
"num_position_embeddings": 2304,
"out_hidden_size": 2560,
"output_attentions": false,
"output_hidden_states": false,
"patch_size": 16,
"problem_type": null,
"return_dict": true,
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"vision_end_token_id": 248054,
"vision_start_token_id": 248053
}
}