Upload model

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,159 @@
+{
+  "architectures": [
+    "Sam3Model"
+  ],
+  "detr_decoder_config": {
+    "box_rpb_mode": "log",
+    "dropout": 0.1,
+    "hidden_act": "relu",
+    "hidden_dropout": 0.0,
+    "hidden_size": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_detr_decoder",
+    "num_attention_heads": 8,
+    "num_layers": 6,
+    "num_queries": 200,
+    "use_presence_token": true
+  },
+  "detr_encoder_config": {
+    "dropout": 0.1,
+    "hidden_act": "relu",
+    "hidden_dropout": 0.0,
+    "hidden_size": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_detr_encoder",
+    "num_attention_heads": 8,
+    "num_layers": 6
+  },
+  "dtype": "float32",
+  "geometry_encoder_config": {
+    "dropout": 0.1,
+    "hidden_act": "relu",
+    "hidden_dropout": 0.0,
+    "hidden_size": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_geometry_encoder",
+    "num_attention_heads": 8,
+    "num_layers": 3,
+    "roi_size": 7
+  },
+  "initializer_range": 0.02,
+  "mask_decoder_config": {
+    "dropout": 0.0,
+    "hidden_size": 256,
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_mask_decoder",
+    "num_attention_heads": 8,
+    "num_upsampling_stages": 3
+  },
+  "model_type": "sam3",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 32,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "projection_dim": 512,
+    "vocab_size": 49408
+  },
+  "transformers_version": "5.0.0.dev0",
+  "vision_config": {
+    "backbone_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "dtype": null,
+      "eos_token_id": null,
+      "finetuning_task": null,
+      "global_attn_indexes": [
+        7,
+        15,
+        23,
+        31
+      ],
+      "hidden_act": "gelu",
+      "hidden_dropout": 0.0,
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 1008,
+      "initializer_range": 0.02,
+      "intermediate_size": 4736,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-06,
+      "layer_scale_init_value": null,
+      "model_type": "sam3_vit_model",
+      "num_attention_heads": 16,
+      "num_channels": 3,
+      "num_hidden_layers": 32,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": null,
+      "patch_size": 14,
+      "prefix": null,
+      "pretrain_image_size": 336,
+      "problem_type": null,
+      "qkv_bias": true,
+      "return_dict": true,
+      "rope_theta": 10000.0,
+      "sep_token_id": null,
+      "task_specific_params": null,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "window_size": 24
+    },
+    "backbone_feature_sizes": [
+      [
+        288,
+        288
+      ],
+      [
+        144,
+        144
+      ],
+      [
+        72,
+        72
+      ]
+    ],
+    "fpn_hidden_size": 256,
+    "fpn_kernel_size": 2,
+    "fpn_stride": 2,
+    "hidden_act": "gelu",
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_vision_model",
+    "num_feature_levels": 3,
+    "scale_factors": [
+      4.0,
+      2.0,
+      1.0,
+      0.5
+    ]
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd530ce2a267fc6035b40166e89ebd2bf306b121b891aaf0f7fc37b72649c8fe
+size 3361709632