Update README.md
Browse files
README.md
CHANGED
|
@@ -25,13 +25,6 @@ These models have been trained at scale on high-quality image caption datasets a
|
|
| 25 |
More technical details will come with a technical report soon.
|
| 26 |
|
| 27 |
|
| 28 |
-
# Datasets
|
| 29 |
-
|
| 30 |
-
| Dataset Type| Dataset(s) Used |
|
| 31 |
-
|--------|------------------------------------------|
|
| 32 |
-
| Pretrain | caption data: (datacomp, cc12m, cc3m, SBU, vg) && interleaved data: obelics |
|
| 33 |
-
| Instruction Tuning | LLaVA-Instruct-150K, ShareGPT4V captions, a mixture of academic VQA data including OCR/Document/Chart-focused tasks, publicly available text-only instruction data |
|
| 34 |
-
|
| 35 |
# Results
|
| 36 |
|
| 37 |
### Pretrain (base model without instruction tuning)
|
|
|
|
| 25 |
More technical details will come with a technical report soon.
|
| 26 |
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
# Results
|
| 29 |
|
| 30 |
### Pretrain (base model without instruction tuning)
|