add model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/mt5-small",
+  "_name_or_path": "mt5-small-esquad-multitask",
   "add_prefix": true,
   "architectures": [
     "MT5ForConditionalGeneration"
@@ -8,22 +8,25 @@
   "d_kv": 64,
   "d_model": 512,
   "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
   "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
+  "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "mt5",
   "num_decoder_layers": 8,
   "num_heads": 6,
   "num_layers": 8,
   "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.18.0.dev0",
+  "transformers_version": "4.21.2",
   "use_cache": true,
   "vocab_size": 250101
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb63c5c40cd4c769f2cd8f0187411713ee5b3400ef612dc7cfce7e55234029f6
-size 1200748293
+oid sha256:8924d3793b742602ddbed0d32708eeab0e92f43f67d81bdc04ba5633812201bc
+size 1200724741