Robotics
Safetensors
English
alpamayo2_super
alpamayo
Alpamayo2-Super / config.json
BorisIvanovic's picture
Add Alpamayo 2 Super release candidate (#1)
68da07d
Raw
History Blame Contribute Delete
11.2 kB
{
"architectures": [
"Alpamayo2Super"
],
"cotrain_expert_vlm": false,
"dtype": "bfloat16",
"enable_expert": true,
"encode_as_video": false,
"expert_config": {
"action_in_proj_cfg": {
"_target_": "alpamayo2_super.models.action_in_proj.PerWaypointActionInProjV2",
"hidden_size": 512,
"max_freq": 100.0,
"num_enc_layers": 2,
"num_fourier_feats": 20
},
"action_out_proj_cfg": {
"_target_": "torch.nn.Linear"
},
"action_space_cfg": {
"_target_": "alpamayo2_super.action_space.UnicycleAccelCurvatureActionSpace",
"a_lambda": 0.0001,
"a_ridge": 0.0001,
"accel_bounds": [
-9.8,
9.8
],
"accel_mean": 0.02902694707164455,
"accel_std": 0.6810426736454882,
"curvature_bounds": [
-0.33,
0.33
],
"curvature_mean": 0.0002692167976330542,
"curvature_std": 0.026148280660833106,
"dt": 0.1,
"kappa_lambda": 0.0001,
"kappa_ridge": 0.0001,
"n_waypoints": 64,
"theta_lambda": 1e-06,
"theta_ridge": 1e-08,
"v_lambda": 1e-06,
"v_ridge": 0.0001
},
"cache_layer_indices": null,
"diffusion_cfg": {
"_target_": "alpamayo2_super.diffusion.flow_matching.FlowMatching",
"inference_guidance_weight": 3.0,
"int_method": "euler",
"train_ignore_guidance_rate": 0.1,
"train_timestep_sampler": "beta",
"use_classifier_free_guidance": false,
"x_dims": null
},
"expert_non_causal_attention": true,
"expert_update_cfg": {
"head_dim": 128,
"hidden_size": 1536,
"intermediate_size": 6144,
"num_attention_heads": 16
},
"llm_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_bias": false,
"attention_dropout": 0.0,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 151643,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"dtype": "bfloat16",
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 151645,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1536,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 6144,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 262144,
"min_length": 0,
"model_type": "qwen3_vl_text",
"no_repeat_ngram_size": 0,
"num_attention_heads": 16,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_interleaved": true,
"mrope_section": [
24,
20,
20
],
"rope_type": "default"
},
"rope_theta": 5000000,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": false,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 155776
},
"model_type": "alpamayo2_super_expert"
},
"frame_label": "frame_num",
"future_traj_tokenizer_cfg": {
"_recursive_": false,
"_target_": "alpamayo2_super.action_space.discrete_action_space.DiscreteTrajectoryTokenizer",
"action_space_cfg": {
"_target_": "alpamayo2_super.action_space.UnicycleAccelCurvatureActionSpace",
"a_lambda": 0.0001,
"a_ridge": 0.0001,
"accel_bounds": [
-9.8,
9.8
],
"accel_mean": 0.02902694707164455,
"accel_std": 0.6810426736454882,
"curvature_bounds": [
-0.33,
0.33
],
"curvature_mean": 0.0002692167976330542,
"curvature_std": 0.026148280660833106,
"dt": 0.1,
"kappa_lambda": 0.0001,
"kappa_ridge": 0.0001,
"n_waypoints": 64,
"theta_lambda": 1e-06,
"theta_ridge": 1e-08,
"v_lambda": 1e-06,
"v_ridge": 0.0001
},
"dims_max": [
10,
10
],
"dims_min": [
-10,
-10
],
"num_bins": 3000
},
"future_vocab_size": 3000,
"hist_traj_tokenizer_cfg": {
"_target_": "alpamayo2_super.models.delta_tokenizer.DeltaTrajectoryTokenizer",
"pad_origin_at_beginning": false
},
"history_vocab_size": 1000,
"include_camera_ids": true,
"loss_weights": {
"future_traj": 1.0,
"others": 1.0
},
"max_pixels": 196608,
"min_pixels": 163840,
"model_type": "alpamayo2_super",
"padding_side": "left",
"token_layout": "camera_ts",
"tokens_per_future_traj": 128,
"tokens_per_history_traj": 45,
"traj_ids": {
"future_end": 155683,
"future_id0": 152669,
"future_pad": 155685,
"future_start": 155681,
"history_end": 155676,
"history_id0": 151669,
"history_pad": 155684,
"history_start": 155674
},
"traj_vocab_size": 4000,
"transformers_version": "4.57.6",
"video_max_pixels": null,
"video_min_pixels": null,
"video_pixels_per_frame": false,
"vlm_class": "Qwen3VLForConditionalGeneration",
"vlm_config": {
"_name_or_path": "",
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"dtype": "bfloat16",
"image_token_id": 151655,
"model_type": "qwen3_vl",
"text_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_bias": false,
"attention_dropout": 0.0,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 151643,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"dtype": "bfloat16",
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 151645,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 25600,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 262144,
"min_length": 0,
"model_type": "qwen3_vl_text",
"no_repeat_ngram_size": 0,
"num_attention_heads": 64,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_interleaved": true,
"mrope_section": [
24,
20,
20
],
"rope_type": "default"
},
"rope_theta": 5000000,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": false,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 155776
},
"video_token_id": 151656,
"vision_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"deepstack_visual_indexes": [
8,
16,
24
],
"depth": 27,
"diversity_penalty": 0.0,
"do_sample": false,
"dtype": "bfloat16",
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 4304,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "qwen3_vl",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_heads": 16,
"num_position_embeddings": 2304,
"num_return_sequences": 1,
"out_hidden_size": 5120,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"patch_size": 16,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"spatial_merge_size": 2,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"temporal_patch_size": 2,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"typical_p": 1.0,
"use_bfloat16": false
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652
},
"vlm_name_or_path": ""
}