Upload LongformerEncoderDecoderForConditionalGeneration
Browse files- config.json +78 -0
- generation_config.json +12 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/content/drive/MyDrive/university/Master Of Sience/2/deep learning with nlp/Text Summarization/LED/convert_model_to_long/arman_to_long/arman_8k/",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "relu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": true,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"LongformerEncoderDecoderForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dilation": [
|
| 11 |
+
1,
|
| 12 |
+
1,
|
| 13 |
+
1,
|
| 14 |
+
1,
|
| 15 |
+
1,
|
| 16 |
+
1,
|
| 17 |
+
1,
|
| 18 |
+
1,
|
| 19 |
+
1,
|
| 20 |
+
1,
|
| 21 |
+
1,
|
| 22 |
+
1
|
| 23 |
+
],
|
| 24 |
+
"attention_dropout": 0.1,
|
| 25 |
+
"attention_probs_dropout_prob": 0.1,
|
| 26 |
+
"attention_window": [
|
| 27 |
+
512,
|
| 28 |
+
512,
|
| 29 |
+
512,
|
| 30 |
+
512,
|
| 31 |
+
512,
|
| 32 |
+
512,
|
| 33 |
+
512,
|
| 34 |
+
512,
|
| 35 |
+
512,
|
| 36 |
+
512,
|
| 37 |
+
512,
|
| 38 |
+
512
|
| 39 |
+
],
|
| 40 |
+
"bos_token_id": 0,
|
| 41 |
+
"classif_dropout": 0.0,
|
| 42 |
+
"classifier_dropout": 0.0,
|
| 43 |
+
"d_model": 768,
|
| 44 |
+
"decoder_attention_heads": 12,
|
| 45 |
+
"decoder_ffn_dim": 3072,
|
| 46 |
+
"decoder_layerdrop": 0.0,
|
| 47 |
+
"decoder_layers": 12,
|
| 48 |
+
"decoder_start_token_id": 0,
|
| 49 |
+
"dropout": 0.1,
|
| 50 |
+
"encoder_attention_heads": 12,
|
| 51 |
+
"encoder_ffn_dim": 3072,
|
| 52 |
+
"encoder_layerdrop": 0.0,
|
| 53 |
+
"encoder_layers": 12,
|
| 54 |
+
"eos_token_id": 1,
|
| 55 |
+
"extra_pos_embeddings": 1,
|
| 56 |
+
"force_bos_token_to_be_generated": false,
|
| 57 |
+
"forced_eos_token_id": 1,
|
| 58 |
+
"gradient_checkpointing": false,
|
| 59 |
+
"init_std": 0.02,
|
| 60 |
+
"is_encoder_decoder": true,
|
| 61 |
+
"length_penalty": 0.8,
|
| 62 |
+
"max_decoder_position_embeddings": 512,
|
| 63 |
+
"max_encoder_position_embeddings": 8192,
|
| 64 |
+
"max_length": 256,
|
| 65 |
+
"max_position_embeddings": 8192,
|
| 66 |
+
"model_type": "pegasus",
|
| 67 |
+
"normalize_before": true,
|
| 68 |
+
"normalize_embedding": false,
|
| 69 |
+
"num_beams": 8,
|
| 70 |
+
"num_hidden_layers": 12,
|
| 71 |
+
"pad_token_id": 0,
|
| 72 |
+
"scale_embedding": true,
|
| 73 |
+
"static_position_embeddings": true,
|
| 74 |
+
"torch_dtype": "float32",
|
| 75 |
+
"transformers_version": "4.29.2",
|
| 76 |
+
"use_cache": true,
|
| 77 |
+
"vocab_size": 96103
|
| 78 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 0,
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"forced_eos_token_id": 1,
|
| 7 |
+
"length_penalty": 0.8,
|
| 8 |
+
"max_length": 256,
|
| 9 |
+
"num_beams": 8,
|
| 10 |
+
"pad_token_id": 0,
|
| 11 |
+
"transformers_version": "4.29.2"
|
| 12 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf0c44d4dc98c0f5a125dc13b3036234db39ae67437dd88aa7b4f74714c60862
|
| 3 |
+
size 1196740045
|