Upload 7 files

config.json

@@ -1,47 +1,28 @@
 {
-  "name_or_path": "ai4bharat/indictrans2-indic-en-1B",
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
+  "_name_or_path": "/home/patrick/hugging_face/t5/mt5-large",
   "architectures": [
-    "IndicTransForConditionalGeneration"
+    "MT5ForConditionalGeneration"
   ],
-  "auto_map": {
-    "AutoConfig": "configuration_indictrans.IndicTransConfig",
-    "AutoModelForSeq2SeqLM": "modeling_indictrans.IndicTransForConditionalGeneration"
-  },
-  "tokenizer_class": "IndicTransTokenizer",
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "decoder_attention_heads": 16,
-  "decoder_embed_dim": 1024,
-  "decoder_ffn_dim": 8192,
-  "decoder_layerdrop": 0,
-  "decoder_layers": 18,
-  "decoder_normalize_before": true,
-  "decoder_start_token_id": 2,
-  "decoder_vocab_size": 32296,
-  "vocab_size": 32296,
-  "dropout": 0.2,
-  "encoder_attention_heads": 16,
-  "encoder_embed_dim": 1024,
-  "encoder_ffn_dim": 8192,
-  "encoder_layerdrop": 0,
-  "encoder_layers": 18,
-  "encoder_normalize_before": true,
-  "encoder_vocab_size": 122706,
-  "eos_token_id": 2,
-  "init_std": 0.02,
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "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,
-  "layernorm_embedding": false,
-  "max_source_positions": 256,
-  "max_target_positions": 256,
-  "model_type": "IndicTrans",
-  "num_hidden_layers": 18,
-  "pad_token_id": 1,
-  "scale_embedding": true,
-  "share_decoder_input_output_embed": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.32.1",
+  "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_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "transformers_version": "4.2.1",
   "use_cache": true,
-  "attn_implementation": "eager"
+  "vocab_size": 250112
 }

gitattributes

@@ -1,36 +1,17 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
-model.SRC filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

pytorch_model (2).bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a895c9c86e07cf5b4034bc7604a53f8393a1cf2381b77013a44e6416d4a289d7
+size 4918521655

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95ae59f5148766cef4801353d7d3166f623078ea078ad49eba84c202381e5d3
-size 4092276281
+oid sha256:a895c9c86e07cf5b4034bc7604a53f8393a1cf2381b77013a44e6416d4a289d7
+size 4918521655

special_tokens_map.json

@@ -1,6 +1 @@
-{
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
-}
+{"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:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer_config.json

@@ -1,51 +1 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
-  "do_lower_case": false,
-  "eos_token": "</s>",
-  "model_max_length": 256,
-  "pad_token": "<pad>",
-  "name_or_path": "ai4bharat/indictrans2-indic-en-1B",
-  "tokenizer_class": "IndicTransTokenizer",
-  "auto_map": {
-    "AutoTokenizer": [
-      "tokenization_indictrans.IndicTransTokenizer",
-      null
-    ]
-  },
-  "unk_token": "<unk>"
-}
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "tokenizer_file": null, "name_or_path": "google/mt5-large"}