Upload 11 files

README.md

@@ -1,11 +1,4 @@
----
-license: apache-2.0
-pipeline_tag: image-to-text
-tags:
-- image-to-text
-- image-captioning
----
-## Use in Transformers
+## Usage method:
 ```python
 from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer
 import torch

config.json

@@ -1,10 +1,10 @@
 {
   "_commit_hash": null,
-  "_name_or_path": "./best-pth",
+  "_name_or_path": "./image-captioning-output",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
-  "bos_token_id": 36,
+  "bos_token_id": 50256,
   "decoder": {
     "_name_or_path": "",
     "activation_function": "gelu_new",
@@ -15,16 +15,16 @@
     "attn_pdrop": 0.1,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
-    "bos_token_id": 36,
+    "bos_token_id": 50256,
     "chunk_size_feed_forward": 0,
     "cross_attention_hidden_size": null,
-    "decoder_start_token_id": 36,
+    "decoder_start_token_id": 50256,
     "diversity_penalty": 0.0,
     "do_sample": false,
     "early_stopping": false,
     "embd_pdrop": 0.1,
     "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 36,
+    "eos_token_id": 50256,
     "exponential_decay_length_penalty": null,
     "finetuning_task": null,
     "forced_bos_token_id": null,
@@ -58,7 +58,7 @@
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 36,
+    "pad_token_id": 50256,
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
@@ -92,13 +92,13 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.28.1",
+    "transformers_version": "4.31.0",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 37
+    "vocab_size": 50257
   },
-  "decoder_start_token_id": 36,
+  "decoder_start_token_id": 50256,
   "encoder": {
     "_name_or_path": "",
     "add_cross_attention": false,
@@ -175,14 +175,14 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.28.1",
+    "transformers_version": "4.31.0",
     "typical_p": 1.0,
     "use_bfloat16": false
   },
-  "eos_token_id": 36,
+  "eos_token_id": 50256,
   "is_encoder_decoder": true,
   "model_type": "vision-encoder-decoder",
-  "pad_token_id": 36,
+  "pad_token_id": 50256,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": null

generation_config.json

@@ -1,8 +1,7 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 36,
-  "decoder_start_token_id": 36,
-  "eos_token_id": 36,
-  "pad_token_id": 36,
-  "transformers_version": "4.28.1"
+  "bos_token_id": 50256,
+  "decoder_start_token_id": 50256,
+  "eos_token_id": 50256,
+  "pad_token_id": 50256,
+  "transformers_version": "4.31.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85507ef26553b9b7b332a4e7772207bad2b0fec1f6e1842fbbd63096510ce5c5
-size 827948609
+oid sha256:12fde92ad7047f4dc316ce88e0a922b872d7b3db12bbb61e60f9de17ada6f201
+size 956935293