add t5 model

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/cognitive_comp/ganruyi/hf_models/google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": 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_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.12.5",
+  "use_cache": true,
+  "vocab_size": 32596
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ce8af84829ce18372bd54b24c499fc0a3691aadda2bea59117c48c06c9d607
+size 154929387

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c65feffa65ff0378759778193852083d23349cb1b40c906e9463a12f8076ff32
+size 680811

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "sp_model_kwargs": {}, "name_or_path": "/cognitive_comp/ganruyi/experiments/t5_cn_small_pretrain/Randeng-T5-77M", "special_tokens_map_file": "/cognitive_comp/ganruyi/experiments/t5_cn_small_pretrain/Randeng-T5-77M/special_tokens_map.json", "tokenizer_class": "T5Tokenizer"}