Robotics
Transformers
Safetensors
English
VLA
Libero-Spatial-1 / config.json
Hume-vla's picture
Upload folder using huggingface_hub
a5a9f0b verified
{
"n_obs_steps": 1,
"normalization_mapping": {
"VISUAL": "IDENTITY",
"STATE": "MEAN_STD",
"ACTION": "MEAN_STD"
},
"input_features": {
"observation.images.image": {
"type": "VISUAL",
"shape": [
3,
256,
256
]
},
"observation.images.wrist_image": {
"type": "VISUAL",
"shape": [
3,
256,
256
]
},
"observation.state": {
"type": "STATE",
"shape": [
8
]
}
},
"output_features": {
"action": {
"type": "ACTION",
"shape": [
7
]
}
},
"device": "cpu",
"use_amp": false,
"type": "hume",
"s1_chunk_size": 8,
"s2_chunk_size": 16,
"n_action_steps": 16,
"max_state_dim": 32,
"max_action_dim": 32,
"resize_imgs_with_padding": [
224,
224
],
"empty_cameras": 0,
"adapt_to_pi_aloha": false,
"use_delta_joint_actions_aloha": false,
"tokenizer_max_length": 48,
"proj_width": 1024,
"num_steps": 10,
"use_cache": true,
"attention_implementation": "eager",
"freeze_vision_encoder": true,
"train_expert_only": false,
"train_state_proj": true,
"optimizer_lr": 5e-05,
"optimizer_betas": [
0.9,
0.95
],
"optimizer_eps": 1e-08,
"optimizer_weight_decay": 1e-10,
"scheduler_warmup_steps": 1000,
"scheduler_decay_steps": 1600000,
"scheduler_decay_lr": 2.5e-06,
"freeze_s2": true,
"s1_his_state_size": 4,
"cache_s2_actions": false,
"theta2": 1.0,
"theta1": 1.0,
"noise_slides_eps": 0.0,
"noise_slides_alp": 0.0,
"s1_proj_width": 512,
"freeze_s1_vision_encoder": false,
"s1_num_steps": 10,
"num_pos": 3,
"discount": 0.98,
"actor_lr": 1e-05,
"critic_lr": 1e-05,
"temp_lr": 2e-05,
"qf_lr": 0.0003,
"next_obs_offset": 1,
"vqh_chunk_size": 1,
"paligemma_config": {
"bos_token_id": 2,
"eos_token_id": 1,
"hidden_size": 2048,
"ignore_index": -100,
"image_token_index": 257152,
"model_type": "paligemma",
"pad_token_id": 0,
"projection_dim": 2048,
"text_config": {
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 2048,
"intermediate_size": 16384,
"model_type": "gemma",
"num_attention_heads": 8,
"num_hidden_layers": 18,
"num_image_tokens": 256,
"num_key_value_heads": 1,
"torch_dtype": "float32",
"vocab_size": 257152
},
"torch_dtype": "float32",
"transformers_version": "4.48.1",
"vision_config": {
"hidden_size": 1152,
"intermediate_size": 4304,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 27,
"num_image_tokens": 256,
"patch_size": 14,
"projection_dim": 2048,
"projector_hidden_act": "gelu_fast",
"vision_use_head": false
},
"vocab_size": 257152
},
"gemma_expert_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 2,
"eos_token_id": 1,
"head_dim": 256,
"hidden_act": "gelu_pytorch_tanh",
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"max_position_embeddings": 8192,
"model_type": "gemma",
"num_attention_heads": 8,
"num_hidden_layers": 18,
"num_key_value_heads": 1,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"rope_theta": 10000.0,
"torch_dtype": "float32",
"transformers_version": "4.48.1",
"use_cache": true,
"vocab_size": 257152
},
"s1_dino_config": {
"return_dict": true,
"output_hidden_states": false,
"output_attentions": false,
"torchscript": false,
"torch_dtype": "float32",
"use_bfloat16": false,
"tf_legacy_loss": false,
"pruned_heads": {},
"tie_word_embeddings": true,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"is_decoder": false,
"cross_attention_hidden_size": null,
"add_cross_attention": false,
"tie_encoder_decoder": false,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"typical_p": 1.0,
"repetition_penalty": 1.0,
"length_penalty": 1.0,
"no_repeat_ngram_size": 0,
"encoder_no_repeat_ngram_size": 0,
"bad_words_ids": null,
"num_return_sequences": 1,
"output_scores": false,
"return_dict_in_generate": false,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"remove_invalid_values": false,
"exponential_decay_length_penalty": null,
"suppress_tokens": null,
"begin_suppress_tokens": null,
"architectures": [
"Dinov2Model"
],
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"tokenizer_class": null,
"prefix": null,
"bos_token_id": null,
"pad_token_id": null,
"eos_token_id": null,
"sep_token_id": null,
"decoder_start_token_id": null,
"task_specific_params": null,
"problem_type": null,
"_name_or_path": "../pretrained/dinov2-small",
"_attn_implementation_autoset": false,
"transformers_version": "4.52.0.dev0",
"model_type": "dinov2",
"hidden_size": 384,
"num_hidden_layers": 12,
"num_attention_heads": 6,
"mlp_ratio": 4,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.0,
"attention_probs_dropout_prob": 0.0,
"initializer_range": 0.02,
"layer_norm_eps": 1e-06,
"image_size": 518,
"patch_size": 14,
"num_channels": 3,
"qkv_bias": true,
"layerscale_value": 1.0,
"drop_path_rate": 0.0,
"use_swiglu_ffn": false,
"stage_names": [
"stem",
"stage1",
"stage2",
"stage3",
"stage4",
"stage5",
"stage6",
"stage7",
"stage8",
"stage9",
"stage10",
"stage11",
"stage12"
],
"apply_layernorm": true,
"reshape_hidden_states": true,
"use_mask_token": true,
"out_features": [
"stage12"
],
"out_indices": [
12
]
},
"s1_gemma_expert_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 2,
"eos_token_id": 1,
"head_dim": 128,
"hidden_act": "gelu_pytorch_tanh",
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 512,
"initializer_range": 0.02,
"intermediate_size": 2048,
"max_position_embeddings": 8192,
"model_type": "gemma",
"num_attention_heads": 8,
"num_hidden_layers": 13,
"num_key_value_heads": 1,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"rope_theta": 10000.0,
"torch_dtype": "float32",
"transformers_version": "4.48.1",
"use_cache": true,
"vocab_size": 257152
}
}