Commit
•
082cd68
1
Parent(s):
cf11280
Upload model
Browse files- README.md +11 -15
- config.json +3 -3
- tf_model.h5 +3 -0
README.md
CHANGED
|
@@ -1,18 +1,20 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
-
-
|
| 5 |
model-index:
|
| 6 |
- name: led-large-16384-finetuned-big_patent
|
| 7 |
results: []
|
| 8 |
---
|
| 9 |
|
| 10 |
-
<!-- This model card has been generated automatically according to the information
|
| 11 |
-
|
| 12 |
|
| 13 |
# led-large-16384-finetuned-big_patent
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -31,14 +33,8 @@ More information needed
|
|
| 31 |
### Training hyperparameters
|
| 32 |
|
| 33 |
The following hyperparameters were used during training:
|
| 34 |
-
-
|
| 35 |
-
-
|
| 36 |
-
- eval_batch_size: 4
|
| 37 |
-
- seed: 42
|
| 38 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 39 |
-
- lr_scheduler_type: linear
|
| 40 |
-
- num_epochs: 1
|
| 41 |
-
- mixed_precision_training: Native AMP
|
| 42 |
|
| 43 |
### Training results
|
| 44 |
|
|
@@ -46,7 +42,7 @@ The following hyperparameters were used during training:
|
|
| 46 |
|
| 47 |
### Framework versions
|
| 48 |
|
| 49 |
-
- Transformers 4.
|
| 50 |
-
-
|
| 51 |
-
- Datasets 2.
|
| 52 |
- Tokenizers 0.12.1
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
+
- generated_from_keras_callback
|
| 5 |
model-index:
|
| 6 |
- name: led-large-16384-finetuned-big_patent
|
| 7 |
results: []
|
| 8 |
---
|
| 9 |
|
| 10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 11 |
+
probably proofread and complete it, then remove this comment. -->
|
| 12 |
|
| 13 |
# led-large-16384-finetuned-big_patent
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [robingeibel/led-large-16384-finetuned-big_patent](https://huggingface.co/robingeibel/led-large-16384-finetuned-big_patent) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
+
- optimizer: None
|
| 37 |
+
- training_precision: float32
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
### Training results
|
| 40 |
|
|
|
|
| 42 |
|
| 43 |
### Framework versions
|
| 44 |
|
| 45 |
+
- Transformers 4.22.1
|
| 46 |
+
- TensorFlow 2.8.2
|
| 47 |
+
- Datasets 2.5.1
|
| 48 |
- Tokenizers 0.12.1
|
config.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"_num_labels": 3,
|
| 4 |
"activation_dropout": 0.0,
|
| 5 |
"activation_function": "gelu",
|
| 6 |
"architectures": [
|
| 7 |
-
"
|
| 8 |
],
|
| 9 |
"attention_dropout": 0.0,
|
| 10 |
"attention_window": [
|
|
@@ -62,7 +62,7 @@
|
|
| 62 |
"pad_token_id": 1,
|
| 63 |
"prefix": " ",
|
| 64 |
"torch_dtype": "float32",
|
| 65 |
-
"transformers_version": "4.
|
| 66 |
"use_cache": true,
|
| 67 |
"vocab_size": 50265
|
| 68 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "robingeibel/led-large-16384-finetuned-big_patent",
|
| 3 |
"_num_labels": 3,
|
| 4 |
"activation_dropout": 0.0,
|
| 5 |
"activation_function": "gelu",
|
| 6 |
"architectures": [
|
| 7 |
+
"LEDModel"
|
| 8 |
],
|
| 9 |
"attention_dropout": 0.0,
|
| 10 |
"attention_window": [
|
|
|
|
| 62 |
"pad_token_id": 1,
|
| 63 |
"prefix": " ",
|
| 64 |
"torch_dtype": "float32",
|
| 65 |
+
"transformers_version": "4.22.1",
|
| 66 |
"use_cache": true,
|
| 67 |
"vocab_size": 50265
|
| 68 |
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45b4635156063726004f7f3fd5a15c9804e9548848e7615279410348ef7cc89c
|
| 3 |
+
size 1839835352
|