Instructions to use AMHR/T5-for-Adversarial-Paraphrasing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AMHR/T5-for-Adversarial-Paraphrasing with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("AMHR/T5-for-Adversarial-Paraphrasing") model = AutoModelForSeq2SeqLM.from_pretrained("AMHR/T5-for-Adversarial-Paraphrasing") - Notebooks
- Google Colab
- Kaggle
coderpotter commited on
Commit ·
595ca4a
1
Parent(s): f31482e
add model
Browse files- config.json +5 -1
- pytorch_model.bin +3 -0
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
|
@@ -10,6 +10,7 @@
|
|
| 10 |
"dropout_rate": 0.1,
|
| 11 |
"eos_token_id": 1,
|
| 12 |
"feed_forward_proj": "relu",
|
|
|
|
| 13 |
"initializer_factor": 1.0,
|
| 14 |
"is_encoder_decoder": true,
|
| 15 |
"layer_norm_epsilon": 1e-06,
|
|
@@ -50,5 +51,8 @@
|
|
| 50 |
"prefix": "translate English to Romanian: "
|
| 51 |
}
|
| 52 |
},
|
|
|
|
|
|
|
|
|
|
| 53 |
"vocab_size": 32128
|
| 54 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": ".",
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 10 |
"dropout_rate": 0.1,
|
| 11 |
"eos_token_id": 1,
|
| 12 |
"feed_forward_proj": "relu",
|
| 13 |
+
"gradient_checkpointing": false,
|
| 14 |
"initializer_factor": 1.0,
|
| 15 |
"is_encoder_decoder": true,
|
| 16 |
"layer_norm_epsilon": 1e-06,
|
|
|
|
| 51 |
"prefix": "translate English to Romanian: "
|
| 52 |
}
|
| 53 |
},
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.9.0",
|
| 56 |
+
"use_cache": true,
|
| 57 |
"vocab_size": 32128
|
| 58 |
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:753b3a95b87968de0150b34ef908b6f341c6993dd42b94f46cd5e3808a4aedb0
|
| 3 |
+
size 891731700
|