Hugging Face's logo

tt1225
/
openvla-7b-devel

Image-Text-to-Text
Transformers
Safetensors
English
openvla
feature-extraction
robotics
vla
multimodal
pretraining
custom_code
Model card Files
xet
 Community
tt1225 commited on
Commit
a4e0794
·
verified ·
1 Parent(s): 4f81610

Upload 17 files

Browse files
Files changed (5) hide show
  1. model-00001-of-00003.safetensors +2 -2
  2. model-00002-of-00003.safetensors +2 -2
  3. model-00003-of-00003.safetensors +2 -2
  4. modeling_prismatic.py +0 -2
  5. tokenizer.model +2 -2
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad400726c30db44e20053106096d423ed2c7887b5b1b3be79da8306e27915ec7
3
- size 135
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10d8636256018712c5e5c823d12e22b5797f99bb721bd123bf6bf2379892be85
3
+ size 6948961960
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a32b3491c48a2d9adeadbcbd8820af5f1f34fe18b101934e1959bd663abf5fde
3
- size 135
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2050b14f21d48904d269f48d5a980fecea87cd7b36641d9b0f015e72d1fe216a
3
+ size 6971232040
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbc11afdbbb2ddbc6cc43c34d76897a6fffbf4c6c539e09ff333964d133c5daa
3
- size 135
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea65305a1577f36f721965bf84c8caec0a948ce7ce84d754701637376c531fef
3
+ size 1162406824
modeling_prismatic.py CHANGED
@@ -517,8 +517,6 @@ class OpenVLAForActionPrediction(PrismaticForConditionalGeneration):
517
  # Run VLA inference
518
  generated_ids = self.generate(input_ids, max_new_tokens=self.get_action_dim(unnorm_key), **kwargs)
519
 
520
- print(generated_ids)
521
-
522
  # Extract predicted action tokens and translate into (normalized) continuous actions
523
  predicted_action_token_ids = generated_ids[0, -self.get_action_dim(unnorm_key) :].cpu().numpy()
524
  discretized_actions = self.vocab_size - predicted_action_token_ids
 
517
  # Run VLA inference
518
  generated_ids = self.generate(input_ids, max_new_tokens=self.get_action_dim(unnorm_key), **kwargs)
519
 
 
 
520
  # Extract predicted action tokens and translate into (normalized) continuous actions
521
  predicted_action_token_ids = generated_ids[0, -self.get_action_dim(unnorm_key) :].cpu().numpy()
522
  discretized_actions = self.vocab_size - predicted_action_token_ids
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a8f238a200be6c23fbba0f9a999ab4fe3c09ca303b29805e68cf6659bfb7d89
3
- size 131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723