Upload folder using huggingface_hub

README.md

@@ -1,3 +1,71 @@
 ---
 license: apache-2.0
+datasets:
+- ibrahimhamamci/CT-RATE
+language:
+- en
+pipeline_tag: text-to-3d
+tags:
+- medical
+- ct
+- diffusion
+- controlnet
+- retrieval-augmented-generation
 ---
+
+# RAGText2CT Weights
+
+Weights for **RAGText2CT: Retrieval-Augmented Anatomical Guidance for Text-to-CT Generation**.
+
+This release is independent from `dmolino/text2ct-weights` and contains the full checkpoint set needed by the `RAGText2CT-Release` codebase.
+
+## Included Files
+
+Under `models/`:
+
+- `autoencoder_epoch273.pt`
+- `unet_rflow_200ep.pt`
+- `CLIP3D_Finding_Impression_30ep.pt`
+- `controlnet_rag_best.pt`
+
+Under `configs/`:
+
+- `config_rag_rflow.json`
+
+## What Each Weight Does
+
+- `autoencoder_epoch273.pt`: 3D VAE for latent compression and decoding.
+- `unet_rflow_200ep.pt`: text-conditioned latent diffusion UNet from the Text2CT backbone.
+- `CLIP3D_Finding_Impression_30ep.pt`: CLIP3D report encoder checkpoint.
+- `controlnet_rag_best.pt`: retrieval-guided anatomical ControlNet checkpoint for RAGText2CT.
+
+## Intended Use
+
+These checkpoints are intended for research on text-conditioned 3D CT generation and retrieval-augmented anatomical guidance.
+
+They are not intended for clinical use or diagnostic decision making.
+
+## Code
+
+Use these weights with the companion repository:
+
+- `RAGText2CT-Release`
+
+The code release expects the files to live under `models/` with the names above.
+
+## Notes
+
+- The first three checkpoints are shared with the original Text2CT pipeline.
+- `controlnet_rag_best.pt` is the additional checkpoint specific to the retrieval-augmented extension.
+- Retrieval-bank artifacts such as `impression_embeddings.npy` and `impression_paths.json` are not included in this weights repo.
+
+## Citation
+
+```bibtex
+@article{Molino2026RAGText2CT,
+  title={Retrieval-Augmented Anatomical Guidance for Text-to-CT Generation},
+  author={Molino, Daniele and Caruso, Camillo Maria and Soda, Paolo and Guarrasi, Valerio},
+  year={2026},
+  journal={arXiv preprint arXiv:2603.08305}
+}
+```

config.json

@@ -0,0 +1,6 @@
+{
+  "model_type": "LDM+VAE",
+  "task": "Text Conditioned CT Generation",
+  "framework": "monai",
+  "modality": "ct"
+}

configs/config_rag_rflow.json

@@ -0,0 +1,69 @@
+{
+    "spatial_dims": 3,
+    "image_channels": 1,
+    "latent_channels": 4,
+    "include_body_region": false,
+    "autoencoder_def": {
+        "_target_": "monai.apps.generation.maisi.networks.autoencoderkl_maisi.AutoencoderKlMaisi",
+        "spatial_dims": "@spatial_dims",
+        "in_channels": "@image_channels",
+        "out_channels": "@image_channels",
+        "latent_channels": "@latent_channels",
+        "num_channels": [64, 128, 256],
+        "num_res_blocks": [2, 2, 2],
+        "norm_num_groups": 32,
+        "norm_eps": 1e-06,
+        "attention_levels": [false, false, false],
+        "with_encoder_nonlocal_attn": false,
+        "with_decoder_nonlocal_attn": false,
+        "use_checkpointing": false,
+        "use_convtranspose": false,
+        "norm_float16": true,
+        "num_splits": 4,
+        "dim_split": 1
+    },
+    "diffusion_unet_def": {
+        "_target_": "monai.apps.generation.maisi.networks.diffusion_model_unet_maisi.DiffusionModelUNetMaisi",
+        "with_conditioning": true,
+        "cross_attention_dim": 768,
+        "spatial_dims": "@spatial_dims",
+        "in_channels": "@latent_channels",
+        "out_channels": "@latent_channels",
+        "num_channels": [64, 128, 256, 512],
+        "attention_levels": [false, false, true, true],
+        "num_head_channels": [0, 0, 32, 32],
+        "num_res_blocks": 2,
+        "use_flash_attention": true,
+        "include_top_region_index_input": "@include_body_region",
+        "include_bottom_region_index_input": "@include_body_region",
+        "include_spacing_input": true,
+        "num_class_embeds": 128,
+        "resblock_updown": true,
+        "include_fc": true
+    },
+    "controlnet_def": {
+        "_target_": "monai.apps.generation.maisi.networks.controlnet_maisi.ControlNetMaisi",
+        "spatial_dims": "@spatial_dims",
+        "in_channels": "@latent_channels",
+        "num_channels": [64, 128, 256, 512],
+        "attention_levels": [false, false, true, true],
+        "num_head_channels": [0, 0, 32, 32],
+        "num_res_blocks": 2,
+        "use_flash_attention": true,
+        "conditioning_embedding_in_channels": 8,
+        "conditioning_embedding_num_channels": [8, 32, 64],
+        "num_class_embeds": 128,
+        "resblock_updown": true,
+        "include_fc": true,
+        "with_conditioning": true,
+        "cross_attention_dim": 768
+    },
+    "noise_scheduler": {
+        "_target_": "monai.networks.schedulers.rectified_flow.RFlowScheduler",
+        "num_train_timesteps": 1000,
+        "use_discrete_timesteps": false,
+        "use_timestep_transform": true,
+        "sample_method": "uniform",
+        "scale": 1.4
+    }
+}

models/CLIP3D_Finding_Impression_30ep.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d737b62e2ad8ed2758426fa3562db65ca0840b33416f982c45d8d3bd7fea7130
+size 3143438178

models/autoencoder_epoch273.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8a7a056d0ebc00486edc43c26768bf1c12eaa6df9dd172e34598003be95eb3
+size 83831868

models/controlnet_rag_best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907ceef649c1f165253ee3aba54311e6b971ad12357acfc1eea219fb448db4ff
+size 359767731

models/unet_rflow_200ep.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674f99fd5436d4f857fe6c830ef50a97fa5ae6c181ed51160cf8229a7cc297c3
+size 870898552