z-lab
/

flashvla-pi05-robotwin

vision-language-action

streaming-action-decoding

Model card Files Files and versions

flashvla-pi05-robotwin

16.6 GB

Ctrl+K

Ctrl+K

2 contributors

History: 15 commits

zhijianliu's picture

Model card: real install and eval commands, training config pointers

47c90d4 verified 25 days ago

.gitattributes

1.52 kB
initial commit 3 months ago
README.md

3.47 kB
Model card: real install and eval commands, training config pointers 25 days ago
config.json

2.44 kB
Remove pretrained_path (internal cluster path; unused at load time) 3 months ago
model.safetensors

16.6 GB
xet

Convert to the alias-free PI0.5 layout (813 tensors) about 1 month ago
policy_postprocessor.json

663 Bytes
Add files using upload-large-folder tool 3 months ago
policy_postprocessor_step_0_unnormalizer_processor.safetensors

5.94 kB
xet

Add files using upload-large-folder tool 3 months ago
policy_preprocessor.json

1.92 kB
Fix policy_preprocessor.json: open-source flashvla compat (pi05-flashvla type, drop dev-only fields, hub tokenizer id, flashvla processor step name) 3 months ago
policy_preprocessor_step_2_normalizer_processor.safetensors

5.91 kB
xet

Add files using upload-large-folder tool 3 months ago
train_config.json

8.81 kB
Sanitize train_config.json: drop internal cluster paths, point tokenizer at upstream hub id 3 months ago