Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/logo.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,190 @@
+# WALL-OSS
+
+<div align="left">
+
+<p align="center">
+    <img src="assets/logo.png" width="600"/>
+<p>
+
+<div align="center">
+
+[![Paper](https://img.shields.io/badge/📄%20Paper-PDF-EA1B22?style=for-the-badge&logo=adobeacrobatreader&logoColor=fff)](https://x2robot.cn-wlcb.ufileos.com/wall_oss.pdf)
+&nbsp;&nbsp;
+[![Hugging Face](https://img.shields.io/badge/Hugging%20Face-x--square--robot-FFB000?style=for-the-badge&logo=huggingface&logoColor=000)](https://huggingface.co/x-square-robot)
+&nbsp;&nbsp;
+[![GitHub](https://img.shields.io/badge/GitHub-181717?style=for-the-badge&logo=github&logoColor=fff)](https://github.com/X-Square-Robot/wall-x)
+&nbsp;&nbsp;
+[![Project Page](https://img.shields.io/badge/Project-1E90FF?style=for-the-badge&logo=google-chrome&logoColor=fff)](https://x2robot.com/en/research/68bc2cde8497d7f238dde690)
+
+</div>
+
+</div>
+
+## <a href="https://x2robot.cn-wlcb.ufileos.com/wall_oss.pdf" target="_blank"><strong>WALL-OSS: Igniting VLMs toward the Embodied Space</strong></a>
+
+We introduce **WALL-OSS**, an end-to-end embodied foundation model that leverages large-scale multimodal pretraining to achieve (1) embodiment-aware vision--language understanding, (2) strong language--action association, and (3) robust manipulation capability.
+Our approach employs a tightly coupled architecture and multi-strategies training curriculum that enables Unified Cross-Level CoT—seamlessly unifying instruction reasoning, subgoal decomposition, and fine-grained action synthesis within a single differentiable framework.
+Our results show that WALL-OSS attains high success on complex long-horizon manipulations, demonstrates strong instruction-following capabilities, complex   understanding and reasoning, and outperforms strong baselines, thereby providing a reliable and scalable path from VLMs to embodied foundation models.
+
+## 🎬 Video Demos
+
+<div align="center">
+    <video width="80%" controls>
+        <source src="https://x2robot.com/api/videos/file/wall-oss_top_720p-1.mp4" type="video/mp4">
+        Your browser does not support the video tag.
+    </video>
+    <p><strong>WALL-OSS in Action: Demonstrating advanced manipulation capabilities and embodied AI performance</strong></p>
+</div>
+
+
+
+## 🚀 Quick Start
+
+### Installation
+
+```bash
+# Create conda environment
+conda create --name wallx python=3.10
+conda activate wallx
+
+# Install base requirements
+pip install torch torchvision transformers
+pip install huggingface_hub
+
+# Install Wall-X from GitHub
+git clone https://github.com/X-Square-Robot/wall-x.git
+cd wall-x
+pip install -e .
+```
+
+### Basic Usage
+
+```python
+import torch
+from wall_x.model.qwen2_5_based.modeling_qwen2_5_vl_act import Qwen2_5_VLMoEForAction
+
+# Load the model
+model_path = "X-Square-Robot/wall-oss-flow"  # or your local path
+model = Qwen2_5_VLMoEForAction.from_pretrained(model_path)
+model.eval()
+
+# Configuration
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = model.to(device).bfloat16()
+
+# Your inference code here...
+```
+
+## 🎯 Supervised Fine-Tuning (SFT)
+
+For training Wall-X on your robotics datasets, please refer to our comprehensive training guide:
+
+**📖 [Training Documentation](https://github.com/X-Square-Robot/wall-x/blob/main/workspace/README.md)**
+
+The training process includes:
+- **Dataset Preparation**: How to prepare your robotics datasets in LeRobot format
+- **Configuration Setup**: Detailed configuration for GPU setup, model paths, and robot DOF settings
+- **Training Scripts**: Ready-to-use training scripts with proper hyperparameters
+
+### Quick Training Start
+
+```bash
+# Run training (see workspace/README.md for detailed configuration)
+bash ./workspace/lerobot_example/run.sh
+```
+
+## 🔮 Inference
+
+For detailed inference examples and model evaluation:
+
+**📖 [Inference Documentation](https://github.com/X-Square-Robot/wall-x/blob/main/scripts/)**
+
+### Basic Inference Example
+
+```python
+import torch
+from wall_x.model.qwen2_5_based.modeling_qwen2_5_vl_act import Qwen2_5_VLMoEForAction
+
+# Load model
+model_path = "X-Square-Robot/wall-x"
+model = Qwen2_5_VLMoEForAction.from_pretrained(model_path)
+model.eval()
+
+# Setup
+batch_size = 1
+seq_length = 50
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = model.to(device).bfloat16()
+
+# Prepare inputs (example with synthetic data)
+torch.manual_seed(0)
+input_ids = torch.randint(0, len(model.processor.tokenizer), (batch_size, seq_length), dtype=torch.long)
+attention_mask = torch.ones((batch_size, seq_length), dtype=torch.long)
+moe_token_types = torch.zeros((batch_size, seq_length), dtype=torch.long)
+position_ids = torch.arange(seq_length, dtype=torch.long).unsqueeze(0).expand(batch_size, -1)
+
+# Robotics-specific inputs
+proprioception = torch.randn((batch_size, 1, 20), dtype=torch.float32)  # Joint states
+agent_pos_mask = torch.ones((batch_size, 1, 20), dtype=torch.float32)
+dof_mask = torch.ones((batch_size, 32, 20), dtype=torch.float32)  # DOF mask
+dataset_names = ["x2_normal"]
+
+# Move to device
+inputs = {
+    "input_ids": input_ids.to(device),
+    "attention_mask": attention_mask.to(device),
+    "moe_token_types": moe_token_types.to(device),
+    "position_ids": position_ids.to(device),
+    "proprioception": proprioception.to(device).bfloat16(),
+    "agent_pos_mask": agent_pos_mask.to(device).bfloat16(),
+    "dof_mask": dof_mask.to(device).bfloat16(),
+    "dataset_names": dataset_names,
+    "mode": "validate"
+}
+
+# Run inference
+with torch.no_grad():
+    outputs = model(**inputs)
+    print(f"Output logits shape: {outputs.logits.shape}")
+```
+
+### Advanced Inference Scripts
+
+For production-ready inference and evaluation scripts:
+
+```bash
+# Basic inference test
+python ./scripts/fake_inference.py
+
+# Generate open-loop comparison plots
+python ./scripts/draw_openloop_plot.py
+```
+
+**📁 [View all inference scripts](https://github.com/X-Square-Robot/wall-x/tree/main/scripts)**
+
+## 📚 Complete Documentation
+
+For comprehensive setup, training, and inference instructions:
+
+### 🚀 **[Visit our GitHub Repository](https://github.com/X-Square-Robot/wall-x)**
+
+The repository contains:
+- **Detailed Installation Guide**: Complete environment setup with all dependencies
+- **Training Tutorials**: Step-by-step SFT process with LeRobot datasets
+- **Inference Examples**: Multiple inference scripts and evaluation tools
+- **Configuration Templates**: Ready-to-use configs for different robot setups
+- **Troubleshooting Guide**: Common issues and solutions
+
+## 📄 Cite Us
+
+If you find WALL-OSS models useful, please cite:
+
+```bibtex
+@misc{walloss_paper_2025,
+  title        = {WALL-OSS: Igniting VLMs toward the Embodied Space},
+  author       = {X Square Robot},
+  year         = {2025},
+  howpublished = {\url{https://x2robot.cn-wlcb.ufileos.com/wall_oss.pdf}},
+  note         = {White paper}
+}
+```

chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,106 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "vision_start_token_id": 151652,
+  "vision_end_token_id": 151653,
+  "vision_token_id": 151654,
+  "image_token_id": 151655,
+  "video_token_id": 151656,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 70,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "_attn_implementation": "flash_attention_2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vision_config": {
+    "depth": 32,
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "intermediate_size": 3420,
+    "num_heads": 16,
+    "in_chans": 3,
+    "out_hidden_size": 2048,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "window_size": 112,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "tokens_per_second": 2,
+    "temporal_patch_size": 2
+  },
+  "rope_scaling": {
+    "type": "mrope",
+    "mrope_section": [
+      16,
+      24,
+      24
+    ]
+  },
+  "vocab_size": 151936,
+  "num_experts": 2,
+  "experts":[
+    {
+      "hidden_size": 2048,
+      "intermediate_size": 11008,
+      "hidden_act": "silu"
+    },
+    {
+      "hidden_size": 2048,
+      "intermediate_size": 2048,
+      "hidden_act": "silu"
+    }
+  ],
+  "dof_config": {
+      "follow_left_ee_cartesian_pos": 3,
+      "follow_left_ee_rotation": 3,
+      "follow_left_gripper": 1,
+      "follow_right_ee_cartesian_pos": 3,
+      "follow_right_ee_rotation": 3,
+      "follow_right_gripper": 1,
+      "head_actions": 2,
+      "height": 1,
+      "car_pose": 3
+  },
+  "agent_pos_config": {
+    "follow_left_ee_cartesian_pos": 3,
+    "follow_left_ee_rotation": 3,
+    "follow_left_gripper": 1,
+    "follow_right_ee_cartesian_pos": 3,
+    "follow_right_ee_rotation": 3,
+    "follow_right_gripper": 1,
+    "head_actions": 2,
+    "height": 1,
+    "car_pose": 3
+  },
+  "noise_scheduler": {
+    "beta_alpha": 1.5,
+    "beta_beta": 1.0,
+    "s": 0.999,
+    "num_inference_timesteps": 5
+  },
+  "dim_inputs": [2048,2048],
+  "attention_moe": false,
+  "mlp_moe": true
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "vision-understanding", "allow_remote": true}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.000001,
+  "transformers_version": "4.49.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff409a6f18b6ac70e115db3b80e5010c6044fe9afc938fe2a7788fd717eafaaa
+size 8448201904

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "min_pixels": 3136,
+  "max_pixels": 12845056,
+  "patch_size": 14,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "processor_class": "Qwen2_5_VLProcessor"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5df236d417e062783cda976a6c21955fe386a1dd8fb9aa06f29694a6d3a4de
+size 11826664