l2aggle commited on
Commit
f18be5c
·
1 Parent(s): 2ed0891
Files changed (1) hide show
  1. README.md +88 -0
README.md CHANGED
@@ -1,3 +1,91 @@
1
  ---
2
  license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
  ---
4
+
5
+ # PPTmodel4UnitreeG1
6
+
7
+ This is a post-pre-trained model specifically designed for Unitree G1 robot applications. The model has been fine-tuned using the [Agibot2UnitreeG1Retarget dataset](https://huggingface.co/datasets/l2aggle/Agibot2UnitreeG1Retarget) to enhance its performance on robotic whole-body manipulation.
8
+
9
+ ## Model Description
10
+
11
+ This model underwent post-pre-training using specialized robotics data to improve its understanding and generation capabilities for Unitree G1 humanoid robot applications. The training process leveraged the Agibot2UnitreeG1Retarget dataset, which contains motion retargeting data specifically curated for Unitree G1.
12
+
13
+ ## Dataset
14
+
15
+ The model was trained on the [Agibot2UnitreeG1Retarget dataset](https://huggingface.co/datasets/l2aggle/Agibot2UnitreeG1Retarget), which provides comprehensive motion retargeting data for converting motion patterns to UnitreeG1 robot format.
16
+
17
+ ## Model Files
18
+
19
+ The model consists of the following files:
20
+ - `config.json` - Model configuration
21
+ - `model.safetensors.index.json` - SafeTensors index file
22
+ - `model-00001-of-00002.safetensors` - Model weights (part 1)
23
+ - `model-00002-of-00002.safetensors` - Model weights (part 2)
24
+ - `trainer_state.json` - Training state information
25
+ - `training_args.bin` - Training arguments
26
+ - `experiment_cfg/` - Experimental configuration files
27
+
28
+ ## Download and Usage
29
+
30
+ ### Method 1: Using Hugging Face Hub
31
+
32
+ ```python
33
+ from transformers import AutoModel, AutoTokenizer
34
+
35
+ # Download and load the model
36
+ model = AutoModel.from_pretrained("l2aggle/PPTmodel4UnitreeG1")
37
+ tokenizer = AutoTokenizer.from_pretrained("l2aggle/PPTmodel4UnitreeG1")
38
+ ```
39
+
40
+ ### Method 2: Using Git LFS
41
+
42
+ ```bash
43
+ # Clone the repository
44
+ git clone https://huggingface.co/l2aggle/PPTmodel4UnitreeG1
45
+
46
+ # Navigate to the model directory
47
+ cd PPTmodel4UnitreeG1
48
+ ```
49
+
50
+ ### Method 3: Direct Download
51
+
52
+ You can also download individual files directly from the [model repository](https://huggingface.co/l2aggle/PPTmodel4UnitreeG1/tree/main) on Hugging Face.
53
+
54
+ ## Requirements
55
+
56
+ - Python 3.7+
57
+ - PyTorch
58
+ - Transformers library
59
+ - SafeTensors
60
+
61
+ ## Installation
62
+
63
+ ```bash
64
+ pip install torch transformers safetensors
65
+ ```
66
+
67
+ ## License
68
+
69
+ This model is released under the Apache 2.0 license.
70
+
71
+ <!-- ## Citation
72
+
73
+ If you use this model in your research, please consider citing:
74
+
75
+ ```bibtex
76
+ @misc{pptmodel4unitreeg1,
77
+ title={PPTmodel4UnitreeG1: Post-Pre-trained Model for UnitreeG1 Robot Applications},
78
+ author={l2aggle},
79
+ year={2024},
80
+ url={https://huggingface.co/l2aggle/PPTmodel4UnitreeG1}
81
+ }
82
+ ```
83
+
84
+ ## Related Resources
85
+
86
+ - Dataset: [Agibot2UnitreeG1Retarget](https://huggingface.co/datasets/l2aggle/Agibot2UnitreeG1Retarget)
87
+ - Model Repository: [PPTmodel4UnitreeG1](https://huggingface.co/l2aggle/PPTmodel4UnitreeG1)
88
+
89
+ ## Contact
90
+
91
+ For questions or issues regarding this model, please open an issue in the model repository or contact the author through Hugging Face. -->