Upload model
Browse files- README.md +46 -0
- config.json +52 -0
- 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: xlm-roberta-longformer-large-16384
|
| 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 |
+
# xlm-roberta-longformer-large-16384
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) 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 4.26.0
|
| 45 |
+
- TensorFlow 2.11.0
|
| 46 |
+
- Tokenizers 0.13.2
|
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LongformerModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"attention_window": [
|
| 7 |
+
512,
|
| 8 |
+
512,
|
| 9 |
+
512,
|
| 10 |
+
512,
|
| 11 |
+
512,
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512,
|
| 26 |
+
512,
|
| 27 |
+
512,
|
| 28 |
+
512,
|
| 29 |
+
512,
|
| 30 |
+
512
|
| 31 |
+
],
|
| 32 |
+
"bos_token_id": 0,
|
| 33 |
+
"classifier_dropout": null,
|
| 34 |
+
"eos_token_id": 2,
|
| 35 |
+
"hidden_act": "gelu",
|
| 36 |
+
"hidden_dropout_prob": 0.1,
|
| 37 |
+
"hidden_size": 1024,
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"intermediate_size": 4096,
|
| 40 |
+
"layer_norm_eps": 1e-05,
|
| 41 |
+
"max_position_embeddings": 16386,
|
| 42 |
+
"model_type": "longformer",
|
| 43 |
+
"num_attention_heads": 16,
|
| 44 |
+
"num_hidden_layers": 24,
|
| 45 |
+
"onnx_export": false,
|
| 46 |
+
"pad_token_id": 1,
|
| 47 |
+
"position_embedding_type": "absolute",
|
| 48 |
+
"sep_token_id": 2,
|
| 49 |
+
"transformers_version": "4.26.0",
|
| 50 |
+
"type_vocab_size": 1,
|
| 51 |
+
"vocab_size": 250002
|
| 52 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94480dddb355810389a6501d34a798a2d9a7b1d035a96e4fff3ba2cc1a68284e
|
| 3 |
+
size 2607523688
|