uploading model

README.md

@@ -0,0 +1,15 @@
+# ALBERT Base Spanish
+
+This is an [ALBERT](https://github.com/google-research/albert) model trained on a [big spanish corpora](https://github.com/josecannete/spanish-corpora).
+The model was trained on a single TPU v3-8 with the following hyperparameters and steps/time:
+- LR: 0.0008838834765
+- Batch Size: 960
+- Warmup ratio: 0.00625
+- Warmup steps: 53333.33333
+- Goal steps: 8533333.333
+- Total steps: 3650000
+- Total training time (aprox): 70.4 days.
+
+## Training loss
+
+![https://drive.google.com/uc?export=view&id=1IsxcgMwd7Hl-3bSnNl8W9jUrHJeHtZql](https://drive.google.com/uc?export=view&id=1IsxcgMwd7Hl-3bSnNl8W9jUrHJeHtZql)

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "../convert_models/albert_base_spanish/converted",
+  "architectures": [
+    "AlbertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.8.2",
+  "type_vocab_size": 2,
+  "vocab_size": 31000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d6e4d323d97a89d5f9112abf8d4b2e9af83cfeb7f375702016e2be30c037c0
+size 47789144

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": "[MASK]"}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c98d44f2c8ba92d861c8705ca4386454387ac7070fb00e9cd934f401387656
+size 797897

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57db1136371c009fef73d6700f6570062471080cdbb5a4acdb9d143e5f78cd2e
+size 64088144

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "../albert_tiny", "tokenizer_class": "AlbertTokenizer"}