Any-to-Any
Bagel
Safetensors
English
medical
medical-imaging
brain-mri
multimodal
image-to-image
image-text-to-text
modality-imputation
Instructions to use Astrostellar/UniBrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Bagel
How to use Astrostellar/UniBrain with Bagel:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
zhiyuns commited on
Commit ·
39e4bee
1
Parent(s): 25f28e9
upload stage-3 model
Browse files- README.md +2 -2
- checkpoints_s3/0000200/ema.safetensors +3 -0
- checkpoints_s3/0000200/llm_config.json +27 -0
- checkpoints_s3/0000200/merges.txt +0 -0
- checkpoints_s3/0000200/tokenizer.json +0 -0
- checkpoints_s3/0000200/tokenizer_config.json +1 -0
- checkpoints_s3/0000200/vit_config.json +9 -0
- checkpoints_s3/0000200/vocab.json +0 -0
README.md
CHANGED
|
@@ -58,7 +58,7 @@ The following results are reported on the RadGenome-Brain MRI evaluation split i
|
|
| 58 |
|
| 59 |
### MRI diagnosis and report generation
|
| 60 |
|
| 61 |
-
| Available modalities |
|
| 62 |
| --- | ---: | ---: |
|
| 63 |
| T1w only | 74.47 | 36.93 |
|
| 64 |
| T1w + T2w | 76.60 | 38.23 |
|
|
@@ -67,7 +67,7 @@ The following results are reported on the RadGenome-Brain MRI evaluation split i
|
|
| 67 |
|
| 68 |
### MRI modality imputation
|
| 69 |
|
| 70 |
-
| Imputation sequence | PSNR |
|
| 71 |
| --- | ---: | ---: |
|
| 72 |
| T1w → T2w | 22.23 | 68.09 |
|
| 73 |
| T1w, T2w → T2-FLAIR | 22.58 | 67.38 |
|
|
|
|
| 58 |
|
| 59 |
### MRI diagnosis and report generation
|
| 60 |
|
| 61 |
+
| Available modalities | Acc | ROUGE |
|
| 62 |
| --- | ---: | ---: |
|
| 63 |
| T1w only | 74.47 | 36.93 |
|
| 64 |
| T1w + T2w | 76.60 | 38.23 |
|
|
|
|
| 67 |
|
| 68 |
### MRI modality imputation
|
| 69 |
|
| 70 |
+
| Imputation sequence | PSNR | Acc |
|
| 71 |
| --- | ---: | ---: |
|
| 72 |
| T1w → T2w | 22.23 | 68.09 |
|
| 73 |
| T1w, T2w → T2-FLAIR | 22.58 | 67.38 |
|
checkpoints_s3/0000200/ema.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c5a61933959ccdcbb14c672ce208c87d3cd33441682e36a4177264dea8ee9f3
|
| 3 |
+
size 29214685336
|
checkpoints_s3/0000200/llm_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 3584,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 18944,
|
| 12 |
+
"max_position_embeddings": 32768,
|
| 13 |
+
"max_window_layers": 28,
|
| 14 |
+
"model_type": "qwen2",
|
| 15 |
+
"num_attention_heads": 28,
|
| 16 |
+
"num_hidden_layers": 28,
|
| 17 |
+
"num_key_value_heads": 4,
|
| 18 |
+
"rms_norm_eps": 1e-06,
|
| 19 |
+
"rope_theta": 1000000.0,
|
| 20 |
+
"sliding_window": 131072,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.43.1",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"use_sliding_window": false,
|
| 26 |
+
"vocab_size": 152064
|
| 27 |
+
}
|
checkpoints_s3/0000200/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints_s3/0000200/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints_s3/0000200/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
/volume/med-train/users/cliu05/UFM/code/UniBrain/models/BAGEL-7B-MoT/tokenizer_config.json
|
checkpoints_s3/0000200/vit_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hidden_size": 1152,
|
| 3 |
+
"image_size": 980,
|
| 4 |
+
"intermediate_size": 4304,
|
| 5 |
+
"model_type": "siglip_vision_model",
|
| 6 |
+
"num_attention_heads": 16,
|
| 7 |
+
"num_hidden_layers": 27,
|
| 8 |
+
"patch_size": 14
|
| 9 |
+
}
|
checkpoints_s3/0000200/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|