First version of the IndicXLMv2-alpha for sentiment classification model and tokenizer.,

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/nlsasfs/home/ai4bharat/gramesh/fine-tuning/IndicXLM/tools/indicXLM_sentencepiece_hf2_og_base_paragraphs/",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "amazon_multilingual_corpus",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 200001
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b84b7b4497d354dad1346179254ae42c79b246241e7152a4ef61011d5741cf
+size 958668233

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"src_lang": "en", "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "/nlsasfs/home/ai4bharat/gramesh/fine-tuning/IndicXLM/tools/indicXLM_sentencepiece_hf2_og_base_paragraphs/special_tokens_map.json", "name_or_path": "/nlsasfs/home/ai4bharat/gramesh/fine-tuning/IndicXLM/tools/indicXLM_sentencepiece_hf2_og_base_paragraphs/", "tokenizer_class": "IndicXLMSentencePieceTokenizer"}