Hugging Face's logo

Ethan-pooh
/
rdt-1b-test

Robotics
Transformers
PyTorch
English
multimodal
pretraining
vla
diffusion
rdt
Inference Endpoints
Model card Files Community
Ethan-pooh commited on
Commit
d7320fb
•
1 Parent(s): bc9e32d

End of training

Browse files
Files changed (7) hide show
  1. README.md +15 -0
  2. checkpoint-2/README.md +9 -0
  3. checkpoint-2/config.json +49 -0
  4. checkpoint-4/README.md +9 -0
  5. checkpoint-4/config.json +49 -0
  6. config.json +49 -0
  7. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: mit
4
+ base_model: robotics-diffusion-transformer/rdt-1b
5
+ tags:
6
+ - robotics
7
+ - diffusers
8
+ - pytorch
9
+ - rdt
10
+ inference: true
11
+ ---
12
+
13
+ # RDT - Ethan-pooh/rdt-1b-test
14
+
15
+ This is a RDT model derived from robotics-diffusion-transformer/rdt-1b. The weights were trained using [RDT](https://rdt-robotics.github.io/rdt-robotics/).
checkpoint-2/README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - pytorch_model_hub_mixin
4
+ - model_hub_mixin
5
+ ---
6
+
7
+ This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
8
+ - Library: https://huggingface.co/robotics-diffusion-transformer/rdt-1b
9
+ - Docs: [More Information Needed]
checkpoint-2/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "action_dim": 128,
3
+ "ema": {
4
+ "inv_gamma": 1.0,
5
+ "max_value": 0.9999,
6
+ "min_value": 0.0,
7
+ "power": 0.75,
8
+ "update_after_step": 0
9
+ },
10
+ "img_adaptor": "mlp2x_gelu",
11
+ "img_cond_len": 4374,
12
+ "img_pos_embed_config": [
13
+ [
14
+ "image",
15
+ [
16
+ 2,
17
+ 3,
18
+ -729
19
+ ]
20
+ ]
21
+ ],
22
+ "img_token_dim": 1152,
23
+ "lang_adaptor": "mlp2x_gelu",
24
+ "lang_pos_embed_config": [
25
+ [
26
+ "lang",
27
+ -1024
28
+ ]
29
+ ],
30
+ "lang_token_dim": 4096,
31
+ "max_lang_cond_len": 1024,
32
+ "noise_scheduler": {
33
+ "beta_schedule": "squaredcos_cap_v2",
34
+ "clip_sample": false,
35
+ "num_inference_timesteps": 5,
36
+ "num_train_timesteps": 1000,
37
+ "prediction_type": "sample",
38
+ "type": "ddpm"
39
+ },
40
+ "pred_horizon": 64,
41
+ "rdt": {
42
+ "cond_pos_embed_type": "multimodal",
43
+ "depth": 28,
44
+ "hidden_size": 2048,
45
+ "num_heads": 32
46
+ },
47
+ "state_adaptor": "mlp3x_gelu",
48
+ "state_token_dim": 128
49
+ }
checkpoint-4/README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - pytorch_model_hub_mixin
4
+ - model_hub_mixin
5
+ ---
6
+
7
+ This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
8
+ - Library: https://huggingface.co/robotics-diffusion-transformer/rdt-1b
9
+ - Docs: [More Information Needed]
checkpoint-4/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "action_dim": 128,
3
+ "ema": {
4
+ "inv_gamma": 1.0,
5
+ "max_value": 0.9999,
6
+ "min_value": 0.0,
7
+ "power": 0.75,
8
+ "update_after_step": 0
9
+ },
10
+ "img_adaptor": "mlp2x_gelu",
11
+ "img_cond_len": 4374,
12
+ "img_pos_embed_config": [
13
+ [
14
+ "image",
15
+ [
16
+ 2,
17
+ 3,
18
+ -729
19
+ ]
20
+ ]
21
+ ],
22
+ "img_token_dim": 1152,
23
+ "lang_adaptor": "mlp2x_gelu",
24
+ "lang_pos_embed_config": [
25
+ [
26
+ "lang",
27
+ -1024
28
+ ]
29
+ ],
30
+ "lang_token_dim": 4096,
31
+ "max_lang_cond_len": 1024,
32
+ "noise_scheduler": {
33
+ "beta_schedule": "squaredcos_cap_v2",
34
+ "clip_sample": false,
35
+ "num_inference_timesteps": 5,
36
+ "num_train_timesteps": 1000,
37
+ "prediction_type": "sample",
38
+ "type": "ddpm"
39
+ },
40
+ "pred_horizon": 64,
41
+ "rdt": {
42
+ "cond_pos_embed_type": "multimodal",
43
+ "depth": 28,
44
+ "hidden_size": 2048,
45
+ "num_heads": 32
46
+ },
47
+ "state_adaptor": "mlp3x_gelu",
48
+ "state_token_dim": 128
49
+ }
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "action_dim": 128,
3
+ "ema": {
4
+ "inv_gamma": 1.0,
5
+ "max_value": 0.9999,
6
+ "min_value": 0.0,
7
+ "power": 0.75,
8
+ "update_after_step": 0
9
+ },
10
+ "img_adaptor": "mlp2x_gelu",
11
+ "img_cond_len": 4374,
12
+ "img_pos_embed_config": [
13
+ [
14
+ "image",
15
+ [
16
+ 2,
17
+ 3,
18
+ -729
19
+ ]
20
+ ]
21
+ ],
22
+ "img_token_dim": 1152,
23
+ "lang_adaptor": "mlp2x_gelu",
24
+ "lang_pos_embed_config": [
25
+ [
26
+ "lang",
27
+ -1024
28
+ ]
29
+ ],
30
+ "lang_token_dim": 4096,
31
+ "max_lang_cond_len": 1024,
32
+ "noise_scheduler": {
33
+ "beta_schedule": "squaredcos_cap_v2",
34
+ "clip_sample": false,
35
+ "num_inference_timesteps": 5,
36
+ "num_train_timesteps": 1000,
37
+ "prediction_type": "sample",
38
+ "type": "ddpm"
39
+ },
40
+ "pred_horizon": 64,
41
+ "rdt": {
42
+ "cond_pos_embed_type": "multimodal",
43
+ "depth": 28,
44
+ "hidden_size": 2048,
45
+ "num_heads": 32
46
+ },
47
+ "state_adaptor": "mlp3x_gelu",
48
+ "state_token_dim": 128
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe217f4491ea882b0b52df1cb23ae4e8a11c1328ed29f2ed712e02aad2c02102
3
+ size 2456755578