Instructions to use microsoft/git-base-textvqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/git-base-textvqa with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="microsoft/git-base-textvqa")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("microsoft/git-base-textvqa") model = AutoModelForImageTextToText.from_pretrained("microsoft/git-base-textvqa") - Notebooks
- Google Colab
- Kaggle
Upload GitForCausalLM
Browse files- config.json +2 -1
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -17,6 +17,7 @@
|
|
| 17 |
"model_type": "git",
|
| 18 |
"num_attention_heads": 12,
|
| 19 |
"num_hidden_layers": 6,
|
|
|
|
| 20 |
"pad_token_id": 0,
|
| 21 |
"position_embedding_type": "absolute",
|
| 22 |
"tie_word_embeddings": false,
|
|
@@ -97,7 +98,7 @@
|
|
| 97 |
"top_p": 1.0,
|
| 98 |
"torch_dtype": null,
|
| 99 |
"torchscript": false,
|
| 100 |
-
"transformers_version": "4.
|
| 101 |
"typical_p": 1.0,
|
| 102 |
"use_bfloat16": false
|
| 103 |
},
|
|
|
|
| 17 |
"model_type": "git",
|
| 18 |
"num_attention_heads": 12,
|
| 19 |
"num_hidden_layers": 6,
|
| 20 |
+
"num_image_with_embedding": null,
|
| 21 |
"pad_token_id": 0,
|
| 22 |
"position_embedding_type": "absolute",
|
| 23 |
"tie_word_embeddings": false,
|
|
|
|
| 98 |
"top_p": 1.0,
|
| 99 |
"torch_dtype": null,
|
| 100 |
"torchscript": false,
|
| 101 |
+
"transformers_version": "4.26.0.dev0",
|
| 102 |
"typical_p": 1.0,
|
| 103 |
"use_bfloat16": false
|
| 104 |
},
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0247e8691306d4cba0b9a57a0cf1d4cb09981fa768377ef69bfb294a26ace29f
|
| 3 |
+
size 708756315
|