MCPcopy Create free account

hub / github.com/SpatialVLA/SpatialVLA / types & classes

Types & classes35 in github.com/SpatialVLA/SpatialVLA

⨍ Functions 244◇ Types & classes 35↳ Endpoints 1
↓ 5 callersClassGemma2RMSNorm
model/modeling_gemma2.py:60
↓ 3 callersClassGemma2Model
Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`Gemma2DecoderLayer`] Args: config: Gemma2Conf
model/modeling_gemma2.py:647
↓ 3 callersClassSpatialActionTokenizer
model/action_tokenizer.py:249
↓ 2 callersClassGemma2ForCausalLM
model/modeling_gemma2.py:887
↓ 2 callersClassSaveProcessorCallback
train/monkey_patch.py:332
↓ 2 callersClassSpatialVLAProcessor
model/processing_spatialvla.py:35
↓ 1 callersClassEgo3DPositionEmbeddingMLP
Absolute pos embedding, learned. https://github.com/kwea123/nerf_pl/blob/52aeb387da64a9ad9a0f914ea9b049ffc598b20c/models/nerf.py#L4
model/modeling_spatialvla.py:41
↓ 1 callersClassGemma2Attention
Multi-headed attention from 'Attention Is All You Need' paper
model/modeling_gemma2.py:325
↓ 1 callersClassGemma2DecoderLayer
model/modeling_gemma2.py:436
↓ 1 callersClassGemma2MLP
model/modeling_gemma2.py:80
↓ 1 callersClassGemma2RotaryEmbedding
model/modeling_gemma2.py:95
↓ 1 callersClassGripperTokenzier
model/action_tokenizer.py:208
↓ 1 callersClassLengthGroupedSampler
r""" Sampler that samples indices in a way that groups together features of the dataset of roughly the same length while keeping a bit of rand
train/monkey_patch.py:111
↓ 1 callersClassOpenXIterableDataset
Dataset for supervised fine-tuning.
data/dataset.py:16
↓ 1 callersClassRotationTokenizer
model/action_tokenizer.py:143
↓ 1 callersClassSpatialVLACausalLMOutputWithPast
model/modeling_spatialvla.py:113
↓ 1 callersClassSpatialVLAConfig
model/configuration_spatialvla.py:22
↓ 1 callersClassSpatialVLAForConditionalGeneration
model/modeling_spatialvla.py:162
↓ 1 callersClassSpatialVLAMultiModalProjector
model/modeling_spatialvla.py:121
↓ 1 callersClassTranslationTokenizer
model/action_tokenizer.py:59
ClassActionEncoding
data/oxe/configs.py:44
ClassActionTokenizer
model/action_tokenizer.py:14
ClassDataTrainingArguments
Arguments pertaining to what data we are going to input our model for training and eval.
train/spatialvla_pretrain.py:105
ClassDataTrainingArguments
Arguments pertaining to what data we are going to input our model for training and eval.
train/spatialvla_finetune.py:101
ClassGemma2FlashAttention2
model/modeling_gemma2.py:416
ClassGemma2ForSequenceClassification
model/modeling_gemma2.py:1109
ClassGemma2ForTokenClassification
model/modeling_gemma2.py:1205
ClassGemma2PreTrainedModel
model/modeling_gemma2.py:530
ClassGemma2SdpaAttention
model/modeling_gemma2.py:426
ClassModelArguments
Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
train/spatialvla_pretrain.py:56
ClassModelArguments
Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
train/spatialvla_finetune.py:49
ClassNormalizationType
data/utils/data_utils.py:48
ClassProfilerTrainer
train/monkey_patch.py:344
ClassSpatialVLAPreTrainedModel
model/modeling_spatialvla.py:130
ClassStateEncoding
data/oxe/configs.py:33