upload pretrained checkpoint of F1-VLA for initial release

.gitattributes

@@ -33,3 +33,4 @@ 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
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,98 @@
 ---
+pipeline_tag: robotics
+library_name: transformers
 license: cc-by-nc-sa-4.0
+tags:
+  - vision-language-model
+  - manipulation
+  - robotics
 ---
+
+<div align="center">
+  <video src="https://cdn-uploads.huggingface.co/production/uploads/678123194248fde89e4fc9bf/_cbIWKHPzffRxIpfmqdFG.mp4"
+         controls autoplay muted playsinline loop width="720"></video>
+  
+  <p><em>🏁 Best viewed with sound on</em></p>
+</div>
+
+
+# <img src="https://cdn-uploads.huggingface.co/production/uploads/678123194248fde89e4fc9bf/DlaSt8_2mmyyzayK9ymbp.png" alt="F1 Logo" width="70" height="45">: A Vision Language Action Model Bridging<br>Understanding and Generation to Actions
+
+[![Website](https://img.shields.io/badge/Website-Pages-blue.svg)](https://aopolin-lv.github.io/F1-VLA)
+[![Code](https://img.shields.io/badge/GitHub-Code-181717?logo=github)](https://github.com/InternRobotics/F1-VLA)
+
+
+## 🚀 Key Innovations
+
+- **🧠 Predictive Inverse Dynamics**: Visual foresight generation for planning-based control
+- **🏗️ Mixture-of-Transformer**: Three specialized experts (Understanding, Generation, Action)
+- **📈 Three-Stage Training**: Progressive alignment, pretraining, and adaptation
+
+## 🤖 Real-World Robot Experiments
+
+<!-- <div align="center">
+    <video src="https://cdn-uploads.huggingface.co/production/uploads/678123194248fde89e4fc9bf/FPZ45NJd9_B_T1gOP8QVf.qt"
+         controls autoplay muted playsinline loop width="720"></video>
+  <p><em>9 diverse manipulation tasks including pick-and-place, handover, and complex object manipulation</em></p>
+</div> -->
+
+<div style="display: flex; flex-direction: column; align-items: center; gap: 10px;">
+    <!-- First Row -->
+    <div style="display: flex; justify-content: center; align-items: center; gap: 10px;">
+        <video controls autoplay loop muted width="250" style="border-radius: 10px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);">
+            <source src="https://huggingface.co/spaces/Jia-Zeng/Robot_demos/resolve/main/arx_v2_long.mp4" type="video/mp4">
+        </video>
+        <video controls autoplay loop muted width="250" style="border-radius: 10px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);">
+            <source src="https://huggingface.co/spaces/Jia-Zeng/Robot_demos/resolve/main/arx_v1_dyna.mp4" type="video/mp4">
+        </video>
+        <video controls autoplay loop muted width="260" style="border-radius: 10px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);">
+            <source src="https://huggingface.co/spaces/Jia-Zeng/Robot_demos/resolve/main/franka_v1_sweep.mp4" type="video/mp4">
+        </video>
+    </div>
+    <!-- Second Row -->
+    <div style="display: flex; justify-content: center; align-items: center; gap: 10px;">
+        <video controls autoplay loop muted width="250" style="border-radius: 10px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);">
+            <source src="https://huggingface.co/spaces/Jia-Zeng/Robot_demos/resolve/main/genie_v2_handover.mp4" type="video/mp4">
+        </video>
+        <video controls autoplay loop muted width="250" style="border-radius: 10px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);">
+            <source src="https://huggingface.co/spaces/Jia-Zeng/Robot_demos/resolve/main/genie_v3_tea.mp4" type="video/mp4">
+        </video>
+        <video controls autoplay loop muted width="260" style="border-radius: 10px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);">
+            <source src="https://huggingface.co/spaces/Jia-Zeng/Robot_demos/resolve/main/genie_v1_flower.mp4" type="video/mp4">
+        </video>
+    </div>
+    <p><em>Diverse manipulation tasks across multiple robot platforms.</em></p>
+</div>
+
+
+## 📊 Performance Summary
+
+| Task | Platform | F1 | π0 | Improvement |
+|:--------:|:------------:|:------------------:|:------------:|:---------------:|
+| Multi-task | Genie-1 | 82.2% | 65.2% | +17.0% |
+| Adaptation | Franka | 66.7% | 53.3% | +13.4% |
+| Long-horizon | ARX LIFT II | 40.0% | 0.0% | +40.0% |
+| Dynamic Env | ARX LIFT II | 66.7% | 33.3% | +33.4% |
+
+## Usage
+Please refer to our official repo [F1-VLA](https://github.com/InternRobotics/F1-VLA).
+
+## 📚 Citation
+
+If you find our work helpful, please cite:
+
+```bibtex
+@article{f1_vla_2025,
+  title={F1: A Vision Language Action Model Bridging Understanding and Generation to Actions},
+  author={Qi Lv and Weijie Kong and Hao Li and Jia Zeng and Zherui Qiu and Delin Qu and Haoming Song and Qizhi Chen and Xiang Deng and Jiangmiao Pang},
+  journal={Conference/Journal Name},
+  year={2025},
+  url={https://arxiv.org/abs/xxxx.xxxxx}
+}
+```
+
+## License
+This work is under the [cc-by-nc-sa-4.0](LICENSE).
+
+## Acknowledgements
+This repository is based on [Lerobot](https://github.com/huggingface/lerobot), [Any4lerobot](https://github.com/Tavish9/any4lerobot/), and [VAR](https://github.com/FoundationVision/VAR).

config.json

@@ -0,0 +1,251 @@
+{
+  "_attn_implementation_autoset": true,
+  "act_expert_config": {
+    "_attn_implementation_autoset": true,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "head_dim": 256,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "max_position_embeddings": 8192,
+    "model_type": "gemma",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 18,
+    "num_key_value_heads": 1,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 10000.0,
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "vocab_size": 257152
+  },
+  "architectures": [
+    "MWMForConditionalGeneration"
+  ],
+  "attention_implementation": "eager",
+  "auto_map": {
+    "AutoConfig": "configuration_mwm.MWMConfig",
+    "AutoModel": "modeling_mwm.MWMForConditionalGeneration"
+  },
+  "chunk_size": 30,
+  "gen_expert_config": {
+    "_attn_implementation_autoset": true,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "head_dim": 256,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "max_position_embeddings": 8192,
+    "model_type": "gemma",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 18,
+    "num_key_value_heads": 1,
+    "num_resolutions": 4,
+    "pn": "1_2_3_4_5_6_8_10_13_16",
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 10000.0,
+    "temporal_conv_kernel_size": 4,
+    "temporal_conv_stride": 4,
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "vae": {
+      "ch": 160,
+      "share_quant_resi": 4,
+      "test_mode": true,
+      "vae_ckpt": "/fs-computility/efm/shared/model_weights/var/vae_ch160v4096z32.pth",
+      "vocab_size": 4096,
+      "z_channels": 32
+    },
+    "vocab_size": 257152
+  },
+  "language_tokenizer_path": "/fs-computility/efm/shared/model_weights/paligemma-3b-pt-224",
+  "max_action_dim": 32,
+  "max_state_dim": 32,
+  "model_type": "mwm",
+  "num_steps": 10,
+  "pretrained_path": "/fs-computility/efm/shared/model_weights/pi0/lerobot",
+  "proj_width": 1024,
+  "resize_imgs_with_padding": [
+    224,
+    224
+  ],
+  "tokenizer_max_length": 48,
+  "transformers_version": "4.51.3",
+  "und_expert_config": {
+    "_attn_implementation_autoset": true,
+    "_vocab_size": 257152,
+    "bos_token_id": 2,
+    "eos_token_id": 1,
+    "hidden_size": 2048,
+    "image_token_index": 257152,
+    "model_type": "paligemma",
+    "pad_token_id": 0,
+    "projection_dim": 2048,
+    "text_config": {
+      "_attn_implementation_autoset": false,
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": 2,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": 1,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "head_dim": 256,
+      "hidden_act": "gelu_pytorch_tanh",
+      "hidden_activation": "gelu_pytorch_tanh",
+      "hidden_size": 2048,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 16384,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_position_embeddings": 8192,
+      "min_length": 0,
+      "model_type": "gemma",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 8,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 18,
+      "num_image_tokens": 256,
+      "num_key_value_heads": 1,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": 0,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "rms_norm_eps": 1e-06,
+      "rope_theta": 10000.0,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": "float32",
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "vocab_size": 257152
+    },
+    "vision_config": {
+      "_attn_implementation_autoset": false,
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "gelu_pytorch_tanh",
+      "hidden_size": 1152,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 224,
+      "intermediate_size": 4304,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-06,
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "siglip_vision_model",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_channels": 3,
+      "num_hidden_layers": 27,
+      "num_image_tokens": 256,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "patch_size": 14,
+      "prefix": null,
+      "problem_type": null,
+      "projection_dim": 2048,
+      "projector_hidden_act": "gelu_fast",
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": "float32",
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "vision_use_head": false
+    }
+  },
+  "use_cache": true,
+  "use_world_model": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07cc300889ca69912a0f5bcad15bd249c220fc3cb6b5a4f9f7a210faea59c7b6
+size 9670959748

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d845b2e4a7826bbe42519b92e1ba5da6bc86cafed73fc38c1f43529ca568b0e
+size 6456