test_large_mlm

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+spiece.model filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,15 @@
+{
+  "<casename>": 250100,
+  "<claim>": 250111,
+  "<conclusion>": 250105,
+  "<criminal_law>": 250108,
+  "<criminal_reason>": 250110,
+  "<defense_attorney>": 250102,
+  "<fact>": 250103,
+  "<law>": 250109,
+  "<order>": 250112,
+  "<plaintiff_attorney>": 250101,
+  "<reasoning>": 250104,
+  "<subtitle>": 250107,
+  "<title>": 250106
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/mt5-large",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "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": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "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": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 250113
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026790366deb497b4ba5a6964c206711476f31be91a3002c3a34401aadf1f4d0
+size 4918527842

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<casename>",
+    "<plaintiff_attorney>",
+    "<defense_attorney>",
+    "<fact>",
+    "<reasoning>",
+    "<conclusion>",
+    "<title>",
+    "<subtitle>",
+    "<criminal_law>",
+    "<law>",
+    "<criminal_reason>",
+    "<claim>",
+    "<order>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0568cbab8bb0c4a13e8086fe8e77b7cfd62fdb1cde1825c63111848cdb9a558b
+size 16332814

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}