Nima Boscarino
commited on
Commit
·
483f4b4
1
Parent(s):
bcb3a29
add model
Browse files- README.md +46 -0
- config.json +8 -4
- tf_model.h5 +3 -0
README.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_keras_callback
|
| 4 |
+
model-index:
|
| 5 |
+
- name: clip-vit-large-patch14-336
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 10 |
+
probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# clip-vit-large-patch14-336
|
| 13 |
+
|
| 14 |
+
This model was trained from scratch on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- optimizer: None
|
| 36 |
+
- training_precision: float32
|
| 37 |
+
|
| 38 |
+
### Training results
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
### Framework versions
|
| 43 |
+
|
| 44 |
+
- Transformers 4.21.3
|
| 45 |
+
- TensorFlow 2.8.2
|
| 46 |
+
- Tokenizers 0.12.1
|
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"CLIPModel"
|
| 4 |
],
|
|
@@ -59,7 +60,7 @@
|
|
| 59 |
"pad_token_id": 1,
|
| 60 |
"prefix": null,
|
| 61 |
"problem_type": null,
|
| 62 |
-
"projection_dim"
|
| 63 |
"pruned_heads": {},
|
| 64 |
"remove_invalid_values": false,
|
| 65 |
"repetition_penalty": 1.0,
|
|
@@ -68,6 +69,7 @@
|
|
| 68 |
"sep_token_id": null,
|
| 69 |
"task_specific_params": null,
|
| 70 |
"temperature": 1.0,
|
|
|
|
| 71 |
"tie_encoder_decoder": false,
|
| 72 |
"tie_word_embeddings": true,
|
| 73 |
"tokenizer_class": null,
|
|
@@ -75,7 +77,7 @@
|
|
| 75 |
"top_p": 1.0,
|
| 76 |
"torch_dtype": null,
|
| 77 |
"torchscript": false,
|
| 78 |
-
"transformers_version": "4.
|
| 79 |
"typical_p": 1.0,
|
| 80 |
"use_bfloat16": false,
|
| 81 |
"vocab_size": 49408
|
|
@@ -134,6 +136,7 @@
|
|
| 134 |
"num_attention_heads": 16,
|
| 135 |
"num_beam_groups": 1,
|
| 136 |
"num_beams": 1,
|
|
|
|
| 137 |
"num_hidden_layers": 24,
|
| 138 |
"num_return_sequences": 1,
|
| 139 |
"output_attentions": false,
|
|
@@ -143,7 +146,7 @@
|
|
| 143 |
"patch_size": 14,
|
| 144 |
"prefix": null,
|
| 145 |
"problem_type": null,
|
| 146 |
-
"projection_dim"
|
| 147 |
"pruned_heads": {},
|
| 148 |
"remove_invalid_values": false,
|
| 149 |
"repetition_penalty": 1.0,
|
|
@@ -152,6 +155,7 @@
|
|
| 152 |
"sep_token_id": null,
|
| 153 |
"task_specific_params": null,
|
| 154 |
"temperature": 1.0,
|
|
|
|
| 155 |
"tie_encoder_decoder": false,
|
| 156 |
"tie_word_embeddings": true,
|
| 157 |
"tokenizer_class": null,
|
|
@@ -159,7 +163,7 @@
|
|
| 159 |
"top_p": 1.0,
|
| 160 |
"torch_dtype": null,
|
| 161 |
"torchscript": false,
|
| 162 |
-
"transformers_version": "4.
|
| 163 |
"typical_p": 1.0,
|
| 164 |
"use_bfloat16": false
|
| 165 |
},
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "openai/clip-vit-large-patch14-336",
|
| 3 |
"architectures": [
|
| 4 |
"CLIPModel"
|
| 5 |
],
|
|
|
|
| 60 |
"pad_token_id": 1,
|
| 61 |
"prefix": null,
|
| 62 |
"problem_type": null,
|
| 63 |
+
"projection_dim": 768,
|
| 64 |
"pruned_heads": {},
|
| 65 |
"remove_invalid_values": false,
|
| 66 |
"repetition_penalty": 1.0,
|
|
|
|
| 69 |
"sep_token_id": null,
|
| 70 |
"task_specific_params": null,
|
| 71 |
"temperature": 1.0,
|
| 72 |
+
"tf_legacy_loss": false,
|
| 73 |
"tie_encoder_decoder": false,
|
| 74 |
"tie_word_embeddings": true,
|
| 75 |
"tokenizer_class": null,
|
|
|
|
| 77 |
"top_p": 1.0,
|
| 78 |
"torch_dtype": null,
|
| 79 |
"torchscript": false,
|
| 80 |
+
"transformers_version": "4.21.3",
|
| 81 |
"typical_p": 1.0,
|
| 82 |
"use_bfloat16": false,
|
| 83 |
"vocab_size": 49408
|
|
|
|
| 136 |
"num_attention_heads": 16,
|
| 137 |
"num_beam_groups": 1,
|
| 138 |
"num_beams": 1,
|
| 139 |
+
"num_channels": 3,
|
| 140 |
"num_hidden_layers": 24,
|
| 141 |
"num_return_sequences": 1,
|
| 142 |
"output_attentions": false,
|
|
|
|
| 146 |
"patch_size": 14,
|
| 147 |
"prefix": null,
|
| 148 |
"problem_type": null,
|
| 149 |
+
"projection_dim": 768,
|
| 150 |
"pruned_heads": {},
|
| 151 |
"remove_invalid_values": false,
|
| 152 |
"repetition_penalty": 1.0,
|
|
|
|
| 155 |
"sep_token_id": null,
|
| 156 |
"task_specific_params": null,
|
| 157 |
"temperature": 1.0,
|
| 158 |
+
"tf_legacy_loss": false,
|
| 159 |
"tie_encoder_decoder": false,
|
| 160 |
"tie_word_embeddings": true,
|
| 161 |
"tokenizer_class": null,
|
|
|
|
| 163 |
"top_p": 1.0,
|
| 164 |
"torch_dtype": null,
|
| 165 |
"torchscript": false,
|
| 166 |
+
"transformers_version": "4.21.3",
|
| 167 |
"typical_p": 1.0,
|
| 168 |
"use_bfloat16": false
|
| 169 |
},
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d12828ca8f0f3c92194f277b7d893da7f2fb7824d0b99dedb305eb48eb46bb7f
|
| 3 |
+
size 1712454232
|