Upload folder using huggingface_hub
Browse files- README.md +14 -0
- config.json +72 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: es
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
tags:
|
| 5 |
+
- nli
|
| 6 |
+
- spanish
|
| 7 |
+
- bart
|
| 8 |
+
- taller-mecanico
|
| 9 |
+
pipeline_tag: text-classification
|
| 10 |
+
widget:
|
| 11 |
+
- text: "El mecánico apretó el tornillo con la llave inglesa."
|
| 12 |
+
text_pair: "Se utilizó una herramienta manual."
|
| 13 |
+
---
|
| 14 |
+
# BART para NLI en Español (Herramientas de Taller)
|
config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.1,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"add_bias_logits": false,
|
| 5 |
+
"add_final_layer_norm": false,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"BartForSequenceClassification"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.1,
|
| 10 |
+
"bos_token_id": 0,
|
| 11 |
+
"classif_dropout": 0.1,
|
| 12 |
+
"classifier_dropout": 0.0,
|
| 13 |
+
"d_model": 768,
|
| 14 |
+
"decoder_attention_heads": 12,
|
| 15 |
+
"decoder_ffn_dim": 3072,
|
| 16 |
+
"decoder_layerdrop": 0.0,
|
| 17 |
+
"decoder_layers": 6,
|
| 18 |
+
"decoder_start_token_id": 2,
|
| 19 |
+
"dropout": 0.1,
|
| 20 |
+
"dtype": "float32",
|
| 21 |
+
"encoder_attention_heads": 12,
|
| 22 |
+
"encoder_ffn_dim": 3072,
|
| 23 |
+
"encoder_layerdrop": 0.0,
|
| 24 |
+
"encoder_layers": 6,
|
| 25 |
+
"eos_token_id": 2,
|
| 26 |
+
"gradient_checkpointing": false,
|
| 27 |
+
"id2label": {
|
| 28 |
+
"0": "Entailment",
|
| 29 |
+
"1": "Neutral",
|
| 30 |
+
"2": "Contradiction"
|
| 31 |
+
},
|
| 32 |
+
"init_std": 0.02,
|
| 33 |
+
"is_decoder": false,
|
| 34 |
+
"is_encoder_decoder": true,
|
| 35 |
+
"label2id": {
|
| 36 |
+
"Entailment": 0,
|
| 37 |
+
"Neutral": 1,
|
| 38 |
+
"Contradiction": 2
|
| 39 |
+
},
|
| 40 |
+
"max_position_embeddings": 1024,
|
| 41 |
+
"model_type": "bart",
|
| 42 |
+
"normalize_before": false,
|
| 43 |
+
"normalize_embedding": true,
|
| 44 |
+
"num_hidden_layers": 6,
|
| 45 |
+
"pad_token_id": 1,
|
| 46 |
+
"problem_type": "single_label_classification",
|
| 47 |
+
"scale_embedding": false,
|
| 48 |
+
"task_specific_params": {
|
| 49 |
+
"summarization": {
|
| 50 |
+
"length_penalty": 1.0,
|
| 51 |
+
"max_length": 128,
|
| 52 |
+
"min_length": 12,
|
| 53 |
+
"num_beams": 4
|
| 54 |
+
},
|
| 55 |
+
"summarization_cnn": {
|
| 56 |
+
"length_penalty": 2.0,
|
| 57 |
+
"max_length": 142,
|
| 58 |
+
"min_length": 56,
|
| 59 |
+
"num_beams": 4
|
| 60 |
+
},
|
| 61 |
+
"summarization_xsum": {
|
| 62 |
+
"length_penalty": 1.0,
|
| 63 |
+
"max_length": 62,
|
| 64 |
+
"min_length": 11,
|
| 65 |
+
"num_beams": 6
|
| 66 |
+
}
|
| 67 |
+
},
|
| 68 |
+
"tie_word_embeddings": true,
|
| 69 |
+
"transformers_version": "5.0.0",
|
| 70 |
+
"use_cache": false,
|
| 71 |
+
"vocab_size": 50265
|
| 72 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:404d1e75213bc70f1ccc4e46f97db95bdfdc6aaa05abe7b757e7e14873d3a5fc
|
| 3 |
+
size 560083468
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38554c8b19efcace107161050c4a2b4c081541515c50cb7da975285883d63103
|
| 3 |
+
size 5201
|