INVERTO commited on
Commit
490a0e4
·
verified ·
1 Parent(s): 10e4167

Upload trained bird captioning model, tokenizer, image processor, species mapping, and captions

Browse files
Files changed (1) hide show
  1. README.md +13 -1
README.md CHANGED
@@ -1,4 +1,16 @@
1
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  # Bird Captioning and Classification Model (CUB-200-2011)
3
 
4
  This is a fine-tuned VisionEncoderDecoderModel based on `nlpconnect/vit-gpt2-image-captioning`, trained on the CUB-200-2011 dataset for bird species classification and image captioning.
@@ -13,7 +25,7 @@ This is a fine-tuned VisionEncoderDecoderModel based on `nlpconnect/vit-gpt2-ima
13
  - **Best Validation Loss**: 0.0690 (Epoch 3)
14
 
15
  ## Files
16
- - `pytorch_model.bin`: Trained model weights
17
  - `config.json`: Model configuration
18
  - `preprocessor_config.json`: ViTImageProcessor settings
19
  - `tokenizer_config.json`, `vocab.json`: GPT2 tokenizer files
 
1
 
2
+ ---
3
+ language: en
4
+ license: mit
5
+ tags:
6
+ - vision
7
+ - image-captioning
8
+ - image-classification
9
+ - bird-species
10
+ datasets:
11
+ - cub-200-2011
12
+ ---
13
+
14
  # Bird Captioning and Classification Model (CUB-200-2011)
15
 
16
  This is a fine-tuned VisionEncoderDecoderModel based on `nlpconnect/vit-gpt2-image-captioning`, trained on the CUB-200-2011 dataset for bird species classification and image captioning.
 
25
  - **Best Validation Loss**: 0.0690 (Epoch 3)
26
 
27
  ## Files
28
+ - `model.safetensors`: Trained model weights
29
  - `config.json`: Model configuration
30
  - `preprocessor_config.json`: ViTImageProcessor settings
31
  - `tokenizer_config.json`, `vocab.json`: GPT2 tokenizer files