Upload trained summarization model
Browse files- config.json +68 -0
- generation_config.json +11 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"EncoderDecoderModel"
|
| 4 |
+
],
|
| 5 |
+
"decoder": {
|
| 6 |
+
"_name_or_path": "bert-base-uncased",
|
| 7 |
+
"add_cross_attention": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"BertForMaskedLM"
|
| 10 |
+
],
|
| 11 |
+
"attention_probs_dropout_prob": 0.1,
|
| 12 |
+
"classifier_dropout": null,
|
| 13 |
+
"gradient_checkpointing": false,
|
| 14 |
+
"hidden_act": "gelu",
|
| 15 |
+
"hidden_dropout_prob": 0.1,
|
| 16 |
+
"hidden_size": 768,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"is_decoder": true,
|
| 20 |
+
"layer_norm_eps": 1e-12,
|
| 21 |
+
"max_position_embeddings": 512,
|
| 22 |
+
"model_type": "bert",
|
| 23 |
+
"num_attention_heads": 12,
|
| 24 |
+
"num_hidden_layers": 12,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"type_vocab_size": 2,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 30522
|
| 30 |
+
},
|
| 31 |
+
"decoder_start_token_id": 101,
|
| 32 |
+
"early_stopping": null,
|
| 33 |
+
"encoder": {
|
| 34 |
+
"_name_or_path": "bert-base-uncased",
|
| 35 |
+
"architectures": [
|
| 36 |
+
"BertForMaskedLM"
|
| 37 |
+
],
|
| 38 |
+
"attention_probs_dropout_prob": 0.1,
|
| 39 |
+
"classifier_dropout": null,
|
| 40 |
+
"gradient_checkpointing": false,
|
| 41 |
+
"hidden_act": "gelu",
|
| 42 |
+
"hidden_dropout_prob": 0.1,
|
| 43 |
+
"hidden_size": 768,
|
| 44 |
+
"initializer_range": 0.02,
|
| 45 |
+
"intermediate_size": 3072,
|
| 46 |
+
"layer_norm_eps": 1e-12,
|
| 47 |
+
"max_position_embeddings": 512,
|
| 48 |
+
"model_type": "bert",
|
| 49 |
+
"num_attention_heads": 12,
|
| 50 |
+
"num_hidden_layers": 12,
|
| 51 |
+
"position_embedding_type": "absolute",
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"type_vocab_size": 2,
|
| 54 |
+
"use_cache": true,
|
| 55 |
+
"vocab_size": 30522
|
| 56 |
+
},
|
| 57 |
+
"eos_token_id": 102,
|
| 58 |
+
"is_encoder_decoder": true,
|
| 59 |
+
"length_penalty": null,
|
| 60 |
+
"max_length": null,
|
| 61 |
+
"min_length": null,
|
| 62 |
+
"model_type": "encoder-decoder",
|
| 63 |
+
"no_repeat_ngram_size": null,
|
| 64 |
+
"num_beams": null,
|
| 65 |
+
"pad_token_id": 0,
|
| 66 |
+
"torch_dtype": "float32",
|
| 67 |
+
"transformers_version": "4.53.3"
|
| 68 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"early_stopping": true,
|
| 4 |
+
"length_penalty": 2.0,
|
| 5 |
+
"max_length": 128,
|
| 6 |
+
"min_length": 30,
|
| 7 |
+
"no_repeat_ngram_size": 3,
|
| 8 |
+
"num_beams": 4,
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"transformers_version": "4.53.3"
|
| 11 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:305177f14ca1266855e7ad68a23b90553170eccbce6487e51bc40dfc049b309b
|
| 3 |
+
size 989518784
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9997e62cd2ba32790247198ba0c1605e315e2cd652452f9a7720d936e8fb86dc
|
| 3 |
+
size 5432
|