Initial commit

ArabicTransformer6-6-6-TF.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610ad1dff563a5d03269c4ec7940ef72b4298a484e3c56341838fc0849fd41f7
+size 2230197058

config.json

@@ -0,0 +1,37 @@
+{
+  "activation_dropout": 0.0,
+  "architectures": [
+    "FunnelModel"
+  ],
+  "attention_dropout": 0.1,
+  "attention_type": "relative_shift",
+  "block_repeats": [
+    1,
+    1,
+    1
+  ],
+  "block_sizes": [
+    6,
+    6,
+    6
+  ],
+  "d_head": 64,
+  "d_inner": 3072,
+  "d_model": 768,
+  "hidden_act": "gelu_new",
+  "hidden_dropout": 0.1,
+  "initializer_range": 0.1,
+  "initializer_std": null,
+  "layer_norm_eps": 1e-09,
+  "max_position_embeddings": 512,
+  "model_type": "funnel",
+  "n_head": 12,
+  "num_decoder_layers": 2,
+  "pool_q_only": true,
+  "pooling_type": "mean",
+  "rel_attn_type": "factorized",
+  "separate_cls": true,
+  "truncate_seq": true,
+  "type_vocab_size": 3,
+  "vocab_size": 50000
+}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df696c71bec8516b4f7679534ab5b4a240fa828a95e584300986e9c3e8e22c30
+size 706740018

net_config.pytorch.json

@@ -0,0 +1,16 @@
+{
+    "block_size": "6_6_6",
+    "d_embed": 768,
+    "d_head": 64,
+    "d_inner": 3072,
+    "d_model": 768,
+    "dropact": 0.0,
+    "dropatt": 0.1,
+    "dropout": 0.1,
+    "n_head": 12,
+    "pool_q_only": true,
+    "pooling_size": 2,
+    "pooling_type": "mean",
+    "separate_cls": true,
+    "vocab_size": 50000
+}

pytorch_model-base.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f3755ab5fb177a4b532a86a234f5406e41c9e73ae9064dcd838bce5307dcbd
+size 706756926

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb1eba5470ff805f3ab5b733d36077b534f4384fbc344b805d1f026e3a2ba308
+size 768218078