Ayushman72
commited on
Commit
·
0505173
1
Parent(s):
578a261
Revert "Update README.md"
Browse filesThis reverts commit 7657166733c3abeb525aa0258af4270329374542.
- README.md +0 -9
- config.json +0 -12
- model.safetensors +0 -3
README.md
CHANGED
|
@@ -1,12 +1,3 @@
|
|
| 1 |
-
---
|
| 2 |
-
pipeline_tag: text-to-image
|
| 3 |
-
tags:
|
| 4 |
-
- image captioing
|
| 5 |
-
- vit
|
| 6 |
-
- gpt
|
| 7 |
-
- gpt2
|
| 8 |
-
- torch
|
| 9 |
-
---
|
| 10 |
# Image Captioning using ViT and GPT2 architecture
|
| 11 |
|
| 12 |
This is my attempt to make a transformer model which takes image as the input and provides a caption for the image
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Image Captioning using ViT and GPT2 architecture
|
| 2 |
|
| 3 |
This is my attempt to make a transformer model which takes image as the input and provides a caption for the image
|
config.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"attention_dropout": 0.1,
|
| 3 |
-
"depth": 12,
|
| 4 |
-
"emb_dropout": 0.1,
|
| 5 |
-
"embed_dim": 768,
|
| 6 |
-
"mlp_dropout": 0.1,
|
| 7 |
-
"mlp_ratio": 4,
|
| 8 |
-
"num_heads": 12,
|
| 9 |
-
"residual_dropout": 0.1,
|
| 10 |
-
"seq_len": 1024,
|
| 11 |
-
"vocab_size": 50257
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:dfe0f8b507dd74c679453125c45fd63dd5fb4c2d563f374b603dd6d6939b9a4c
|
| 3 |
-
size 1004789512
|
|
|
|
|
|
|
|
|
|
|
|