Upload folder using huggingface_hub

README.md

@@ -0,0 +1,60 @@
+---
+datasets: robometer/RBM-1M
+library_name: lerobot
+license: apache-2.0
+model_name: robometer
+pipeline_tag: robotics
+tags:
+- reward-model
+- lerobot
+- qwen3-vl
+- robotics
+- zero-shot
+- robometer
+- vision-language
+---
+
+# Reward Model Card for robometer
+
+<!-- Provide a quick summary of what the reward model is/does. -->
+
+
+Robometer is a zero-shot general-purpose robotic reward model built on a fine-tuned Qwen3-VL backbone with progress, preference, and success heads. Given a video and a task description it outputs a per-frame progress signal in [0, 1] and a per-frame success probability — suitable for offline reward labelling and for low-frequency reward signals during RL fine-tuning of robot policies.
+
+
+This reward model has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
+See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
+
+---
+
+## How to Get Started with the Reward Model
+
+### Train from scratch
+
+```bash
+lerobot-train \
+  --dataset.repo_id=${HF_USER}/<dataset> \
+  --reward_model.type=robometer \
+  --output_dir=outputs/train/<desired_reward_model_repo_id> \
+  --job_name=lerobot_reward_training \
+  --reward_model.device=cuda \
+  --reward_model.repo_id=${HF_USER}/<desired_reward_model_repo_id> \
+  --wandb.enable=true
+```
+
+_Writes checkpoints to `outputs/train/<desired_reward_model_repo_id>/checkpoints/`._
+
+### Load the reward model in Python
+
+```python
+from lerobot.rewards import make_reward_model
+
+reward_model = make_reward_model(pretrained_path="<hf_user>/<reward_model_repo_id>")
+reward = reward_model.compute_reward(batch)
+```
+
+---
+
+## Model Details
+
+- **License:** apache-2.0

config.json

@@ -0,0 +1,171 @@
+{
+    "type": "robometer",
+    "input_features": {
+        "observation.images.top": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        }
+    },
+    "output_features": {
+        "progress": {
+            "type": "REWARD",
+            "shape": [
+                1
+            ]
+        },
+        "success": {
+            "type": "REWARD",
+            "shape": [
+                1
+            ]
+        }
+    },
+    "device": "cpu",
+    "pretrained_path": "robometer/Robometer-4B",
+    "push_to_hub": false,
+    "repo_id": null,
+    "license": "apache-2.0",
+    "tags": [
+        "reward-model",
+        "vision-language",
+        "qwen3-vl",
+        "zero-shot"
+    ],
+    "private": null,
+    "image_key": "observation.images.top",
+    "task_key": "task",
+    "default_task": null,
+    "max_frames": 8,
+    "reward_output": "progress",
+    "success_threshold": 0.5,
+    "base_model_id": "Qwen/Qwen3-VL-4B-Instruct",
+    "torch_dtype": "bfloat16",
+    "use_multi_image": true,
+    "use_per_frame_progress_token": true,
+    "average_temporal_patches": true,
+    "frame_pooling": "mean",
+    "frame_pooling_attn_temperature": 1.0,
+    "progress_loss_type": "discrete",
+    "progress_discrete_bins": 10,
+    "vlm_config": {
+        "transformers_version": "5.5.4",
+        "architectures": [
+            "Qwen3VLForConditionalGeneration"
+        ],
+        "output_hidden_states": false,
+        "return_dict": true,
+        "dtype": null,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "problem_type": null,
+        "text_config": {
+            "architectures": null,
+            "output_hidden_states": false,
+            "return_dict": true,
+            "dtype": "bfloat16",
+            "chunk_size_feed_forward": 0,
+            "is_encoder_decoder": false,
+            "id2label": {
+                "0": "LABEL_0",
+                "1": "LABEL_1"
+            },
+            "label2id": {
+                "LABEL_0": 0,
+                "LABEL_1": 1
+            },
+            "problem_type": null,
+            "vocab_size": 151674,
+            "hidden_size": 2560,
+            "intermediate_size": 9728,
+            "num_hidden_layers": 36,
+            "num_attention_heads": 32,
+            "num_key_value_heads": 8,
+            "head_dim": 128,
+            "hidden_act": "silu",
+            "max_position_embeddings": 262144,
+            "initializer_range": 0.02,
+            "rms_norm_eps": 1e-06,
+            "use_cache": true,
+            "rope_parameters": {
+                "mrope_interleaved": true,
+                "mrope_section": [
+                    24,
+                    20,
+                    20
+                ],
+                "rope_type": "default",
+                "rope_theta": 5000000
+            },
+            "attention_bias": false,
+            "attention_dropout": 0.0,
+            "pad_token_id": null,
+            "_name_or_path": "",
+            "bos_token_id": 151643,
+            "eos_token_id": 151645,
+            "model_type": "qwen3_vl_text",
+            "tie_word_embeddings": true,
+            "output_attentions": false
+        },
+        "vision_config": {
+            "architectures": null,
+            "output_hidden_states": false,
+            "return_dict": true,
+            "dtype": null,
+            "chunk_size_feed_forward": 0,
+            "is_encoder_decoder": false,
+            "id2label": {
+                "0": "LABEL_0",
+                "1": "LABEL_1"
+            },
+            "label2id": {
+                "LABEL_0": 0,
+                "LABEL_1": 1
+            },
+            "problem_type": null,
+            "depth": 24,
+            "hidden_size": 1024,
+            "hidden_act": "gelu_pytorch_tanh",
+            "intermediate_size": 4096,
+            "num_heads": 16,
+            "in_channels": 3,
+            "patch_size": 16,
+            "spatial_merge_size": 2,
+            "temporal_patch_size": 2,
+            "out_hidden_size": 2560,
+            "num_position_embeddings": 2304,
+            "deepstack_visual_indexes": [
+                5,
+                11,
+                17
+            ],
+            "initializer_range": 0.02,
+            "_name_or_path": "",
+            "model_type": "qwen3_vl",
+            "output_attentions": false
+        },
+        "image_token_id": 151655,
+        "video_token_id": 151656,
+        "vision_start_token_id": 151652,
+        "vision_end_token_id": 151653,
+        "tie_word_embeddings": true,
+        "_name_or_path": "Qwen/Qwen3-VL-4B-Instruct",
+        "model_type": "qwen3_vl",
+        "output_attentions": false
+    },
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "REWARD": "IDENTITY"
+    }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013709f2ea0b67aa50385b5c5ae61843cf7f2932b8aab7f5e45e0747560d0c14
+size 8894103800