Upload 9 files

.gitattributes

@@ -33,3 +33,4 @@ 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
+model.TGT filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "ai4bharat/indictrans2-en-indic-1B",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "IndicTransForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attn_implementation": "eager",
+  "auto_map": {
+    "AutoConfig": "ai4bharat/indictrans2-en-indic-1B--configuration_indictrans.IndicTransConfig",
+    "AutoModelForSeq2SeqLM": "ai4bharat/indictrans2-en-indic-1B--modeling_indictrans.IndicTransForConditionalGeneration"
+  },
+  "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": 122672,
+  "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": 32322,
+  "eos_token_id": 2,
+  "init_std": 0.02,
+  "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,
+  "tokenizer_class": "IndicTransTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": false
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.47.1"
+}

model.TGT

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9257c8e76b8b607705b959cc3d075656ea33032f7a974e467b8941df6e98d4
+size 3256903

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d41ab36b9a86816afab32582dc2f4e904e2bc60084e7ebad7d936797c5e7f5
+size 4462265272

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "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
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "ai4bharat/indictrans2-en-indic-1B--tokenization_indictrans.IndicTransTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "src_vocab_file": "/home/debtanu/.cache/huggingface/hub/models--ai4bharat--indictrans2-en-indic-1B/snapshots/fba89d6196ad6c0bbe0031bf3e44fe17313e94f1/dict.SRC.json",
+  "tgt_vocab_file": "/home/debtanu/.cache/huggingface/hub/models--ai4bharat--indictrans2-en-indic-1B/snapshots/fba89d6196ad6c0bbe0031bf3e44fe17313e94f1/dict.SRC.json",
+  "tokenizer_class": "IndicTransTokenizer",
+  "unk_token": "<unk>"
+}