update

README.md

@@ -1,3 +1,25 @@
 ---
 license: cc-by-4.0
 ---
+
+# FiD model trained on WebQ
+
+-- This is the model checkpoint of FiD [2], based on the T5 large (with 770M parameters) and trained on the WebQ dataset [1]. 
+
+-- Hyperparameters: 8 x 40GB A100 GPUs; batch size 8; AdamW; LR 3e-5; 30000 steps
+
+References: 
+
+[1] Semantic parsing on freebase from question-answer pairs. EMNLP 2013.
+
+[2] Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. EACL 2021. 
+
+## Model performance 
+
+We evaluate it on the WebQ dataset, the EM score is 50.2 on the test set.
+
+
+<a href="https://huggingface.co/exbert/?model=bert-base-uncased">
+	<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
+</a>
+

config.json

@@ -0,0 +1,51 @@
+{
+  "architectures": [
+    "FiDT5"
+  ],
+  "d_ff": 4096,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "vocab_size": 32128
+}