Upload Bilma

README.md

@@ -1,20 +1,46 @@
 ---
-library_name: keras
-license: mit
-language:
-- es
+tags:
+- generated_from_keras_callback
+model-index:
+- name: bilma
+  results: []
 ---
-# Descripción
-Bilma es un modelo de Lenguage Natural para el español de los países AR, CL, CO, MX, ES, UY, VE, y US.
 
-# Usos
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
 
-# Datos de entrenamiento
+# bilma
 
-# Resultados
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
 
----
-license: mit
-language:
-- es
----
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: None
+- training_precision: float32
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.30.2
+- TensorFlow 2.4.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,13 @@
+{
+  "architectures": [
+    "lma"
+  ],
+  "drop_rate": 0.1,
+  "embedding_dim": 512,
+  "model_type": "bilma",
+  "num_attention_heads": 4,
+  "num_encoders": 2,
+  "transformers_version": "4.30.2",
+  "vocab_size": 28949,
+  "weights": "spanish"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e6edcfb9e776472ee42b2a7dec322c82ca6be009b35b2506b1be39ad72734ba
+size 156561684