Upload BlipForConditionalGeneration

README.md

@@ -1,22 +1,19 @@
 ---
-pipeline_tag: image-to-text
+license: bsd-3-clause
 tags:
 - image-captioning
+datasets:
+- unography/laion-14k-GPT4V-LIVIS-Captions
+pipeline_tag: image-to-text
 languages:
 - en
-license: bsd-3-clause
 widget:
-- src: >-
-    https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg
   example_title: Savanna
-- src: >-
-    https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg
   example_title: Football Match
-- src: >-
-    https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg
   example_title: Airport
-datasets:
-- unography/laion-14k-GPT4V-LIVIS-Captions
 inference:
   parameters:
     max_length: 300

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Salesforce/blip-image-captioning-large",
+  "_name_or_path": "unography/blip-large-long-cap",
   "architectures": [
     "BlipForConditionalGeneration"
   ],
@@ -17,7 +17,7 @@
     "num_attention_heads": 12
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.40.1",
   "vision_config": {
     "dropout": 0.0,
     "hidden_size": 1024,

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 30522,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.40.0"
+  "transformers_version": "4.40.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252dbdd8eebd5297072b653f7bf7f5582222ea5763670d6b2f8b80e3a7c695db
+oid sha256:08751d62cf395820b3a2b32eea251f9931a6456f5e6d4bb2f015b8173d4d9e02
 size 1879010480