Release GeoUG-Depth EMA checkpoint and model card

README.md

@@ -0,0 +1,90 @@
+---
+license: other
+library_name: bagel-mot
+tags:
+  - geoug
+  - metric-depth
+  - depth-estimation
+---
+
+# GeoUG-Depth
+
+Metric-depth generation expert from training run
+`20260502_bagel_depth_metric_multi_dsp_scaling_2_0006000`, packaged from its
+EMA checkpoint. The source EMA was F32; this upload copy is converted to BF16
+because GeoUG inference loads the model and runs it in BF16. The source
+checkpoint is unchanged.
+
+This model generates a metric depth map in meters from a single RGB image. It
+is intended for standalone metric-depth inference and evaluation. The spatial
+RL checkpoint contains its own jointly trained depth generator and does not
+load this package at runtime.
+
+## Recommended configuration
+
+- Transform: `configs/inference/metric_depth.yaml`
+- Prompt: `<GENERATE_DEPTH>Estimate the metric depth map.</GENERATE_DEPTH>`
+- Weights: EMA (`--is-ema`, the default)
+- Depth generation: 50 timesteps, text CFG 4.0, image CFG 1.5
+
+The default prompt is recommended unless the model is being evaluated with a
+specific field-of-view protocol.
+
+Run from the GeoUG repository root:
+
+```bash
+python -m inference.depth \
+  --model-path ckpt/geoug-metric-depth \
+  --image /path/to/image.jpg \
+  --output-dir outputs/inference/depth
+```
+
+For benchmark evaluation:
+
+```bash
+python -m evaluation.depth.eval_depth \
+  --dataset-config configs/eval/my_depth_datasets.json \
+  --depth-type metric
+```
+
+The `.npy` inference output contains metric depth. The PNG output is only a
+percentile-normalized visualization and must not be used as metric data.
+
+## License
+
+The checkpoint accompanies the mixed-license GeoUG code release. Review the
+repository `LICENSE` and `THIRD_PARTY_NOTICES.md`, including the CC BY-NC
+restrictions on the listed BAGEL/DiT-derived files, before use.
+
+## Package contents
+
+The repository root contains the BAGEL model configs and tokenizer,
+`ae.safetensors`, BF16 `ema.safetensors` with `format=pt` metadata,
+`transform_config.yaml`, this model card, and `checksums.sha256`. No non-EMA
+model or evaluation outputs are included.
+
+## Download
+
+```python
+from huggingface_hub import snapshot_download
+
+snapshot_download(
+    repo_id="rayruiyang/GeoUG-Depth",
+    local_dir="ckpt/geoug-metric-depth",
+)
+```
+
+Use the GeoUG code and its documented environment to load this package. These
+are custom BAGEL/MoT weights, not a standalone `AutoModel.from_pretrained`
+Transformers package. The inference loader selects `ema.safetensors` by default.
+
+## Related releases
+
+| Model | Role |
+|---|---|
+| [GeoUG-Spatial](https://huggingface.co/rayruiyang/GeoUG-Spatial) | Final adaptive spatial reasoning policy |
+| [GeoUG-Depth](https://huggingface.co/rayruiyang/GeoUG-Depth) | Standalone metric-depth generation |
+| [GeoUG-ColdStart](https://huggingface.co/rayruiyang/GeoUG-ColdStart) | SFT initialization for spatial-policy RL |
+
+[Project page](https://yangr116.github.io/geoug-project-page/) ·
+[Paper](https://yangr116.github.io/geoug-project-page/assets/geoug-paper.pdf)

ae.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38
+size 335304388

checksums.sha256

@@ -0,0 +1,12 @@
+709c2037b30808f9fb01b86a61b038bf6779e45671e453bff50ac0a91f431037  README.md
+afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38  ae.safetensors
+6340dfd03b315d68faf266944c2a4a484ec8dafff4f2b55a059d95ad7656cbf7  config.json
+64188ec41156567510ef63e763f4e4531a9ab46675d45714ec94ac2bf9dca925  ema.safetensors
+3a8f9087e486054c8a4a08dae2e5a3ba62e23da212b5b8c08bc42cb983c3459f  generation_config.json
+7463bb0ea78315365e6c6b74de4e73bbcc8359dfb0c5a737584e077d42c0b03c  llm_config.json
+599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3  merges.txt
+c0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539  tokenizer.json
+5b5d4f65d0acd3b2d56a35b56d374a36cbc1c8fa5cf3b3febbbfabf22f359583  tokenizer_config.json
+4e0ff721300a77a0f8d28418aa8f0f699db3cd1ee2b98d1bb2b392e1cf11433a  transform_config.yaml
+917a59e36337e279c9234b6524c653b10de47345761fa4fbb299c64700f20357  vit_config.json
+ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910  vocab.json

config.json

@@ -0,0 +1,3 @@
+{
+  "name": ["BAGEL-7B-MoT"]
+}

ema.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64188ec41156567510ef63e763f4e4531a9ab46675d45714ec94ac2bf9dca925
+size 29214685368

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

llm_config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transform_config.yaml

@@ -0,0 +1,18 @@
+image_transform_args:
+  image_stride: 16
+  max_image_size: 1024
+  min_image_size: 512
+
+depth_transform_args:
+  image_stride: 16
+  max_image_size: 1024
+  min_image_size: 512
+  kitti_bm_crop: true
+  depth_normalization:
+    type: multiscale_disparity_transform
+    c: [2.0, 8.0, 32.0]
+
+vit_image_transform_args:
+  image_stride: 14
+  max_image_size: 518
+  min_image_size: 224

vit_config.json

@@ -0,0 +1,9 @@
+{
+    "hidden_size": 1152,
+    "image_size": 980,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+}