Upload smolvla-2000-step (2000 steps)

README.md

@@ -0,0 +1,37 @@
+---
+license: apache-2.0
+tags:
+- lerobot
+- smolvla
+- vla-robotics
+- so-arm101
+library_name: lerobot
+pipeline_tag: robotics
+---
+
+# smolvla-2000-step
+
+VLA 로보틱스 입문서 예제용 SmolVLA 파인튜닝 체크포인트입니다.
+
+## 경로 (GitHub `code/` 와 대응)
+
+| 항목 | 값 |
+|------|-----|
+| 논리 경로 | `vla-robotics/ch08/01-train-smolvla/smolvla-2000-step` |
+| GitHub | [vla-robotics-examples](https://github.com/makepluscode/vla-robotics-examples) |
+| 예제 폴더 | `code/ch08/01-train-smolvla/` |
+| Hub 모델 ID | `makepluscode/ch08-01-train-smolvla-smolvla-2000-step` |
+| 학습 step | 2000 |
+| 데이터셋 | `makepluscode/so_arm101_block_picking_main` |
+| 베이스 | `lerobot/smolvla_base` |
+
+## 로드
+
+```python
+from lerobot.policies.smolvla.modeling_smolvla import SmolVLAPolicy
+
+policy = SmolVLAPolicy.from_pretrained("makepluscode/ch08-01-train-smolvla-smolvla-2000-step")
+```
+
+전·후처리는 동일 폴더의 `policy_preprocessor.json` /
+`policy_postprocessor.json` 을 `from_pretrained` 로 함께 로드합니다.

config.json

@@ -0,0 +1,93 @@
+{
+    "type": "smolvla",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.images.top": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                128,
+                128
+            ]
+        },
+        "observation.images.side": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": false,
+    "push_to_hub": true,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "chunk_size": 50,
+    "n_action_steps": 50,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "MEAN_STD",
+        "ACTION": "MEAN_STD"
+    },
+    "max_state_dim": 32,
+    "max_action_dim": 32,
+    "resize_imgs_with_padding": [
+        512,
+        512
+    ],
+    "empty_cameras": 0,
+    "adapt_to_pi_aloha": false,
+    "use_delta_joint_actions_aloha": false,
+    "tokenizer_max_length": 48,
+    "num_steps": 10,
+    "use_cache": true,
+    "freeze_vision_encoder": true,
+    "train_expert_only": true,
+    "train_state_proj": true,
+    "optimizer_lr": 0.0001,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 1e-10,
+    "optimizer_grad_clip_norm": 10,
+    "scheduler_warmup_steps": 1000,
+    "scheduler_decay_steps": 30000,
+    "scheduler_decay_lr": 2.5e-06,
+    "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
+    "load_vlm_weights": false,
+    "add_image_special_tokens": false,
+    "attention_mode": "cross_attn",
+    "prefix_length": -1,
+    "pad_language_to": "longest",
+    "num_expert_layers": -1,
+    "num_vlm_layers": 16,
+    "self_attn_every_n_layers": 2,
+    "expert_width_multiplier": 0.75,
+    "min_period": 0.004,
+    "max_period": 4.0,
+    "rtc_config": null,
+    "compile_model": false,
+    "compile_mode": "max-autotune"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8134b81f9d9c9373752d86e2d8b9d7c1645af993c089a5b985ad28b2243e60f
+size 1197789224

policy_postprocessor.json

@@ -0,0 +1,32 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "MEAN_STD",
+          "ACTION": "MEAN_STD"
+        }
+      },
+      "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

policy_postprocessor_step_0_unnormalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95c7ce4f32bdc1a4dac12d91ad65583568d966b8959931bb5dc751e5f16e57b5
+size 7520

policy_preprocessor.json

@@ -0,0 +1,79 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {}
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "smolvla_new_line_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "tokenizer_processor",
+      "config": {
+        "max_length": 48,
+        "task_key": "task",
+        "padding_side": "right",
+        "padding": "longest",
+        "truncation": true,
+        "tokenizer_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
+      }
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "observation.images.top": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              128,
+              128
+            ]
+          },
+          "observation.images.side": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              256,
+              256
+            ]
+          },
+          "observation.state": {
+            "type": "STATE",
+            "shape": [
+              6
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "MEAN_STD",
+          "ACTION": "MEAN_STD"
+        }
+      },
+      "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
+    }
+  ]
+}

policy_preprocessor_step_5_normalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95c7ce4f32bdc1a4dac12d91ad65583568d966b8959931bb5dc751e5f16e57b5
+size 7520