{ "_name_or_path": "ai4bharat/indictrans2-indic-en-1B", "activation_dropout": 0.0, "activation_function": "gelu", "architectures": [ "IndicTransForConditionalGeneration" ], "attention_dropout": 0.0, "attn_implementation": null, "auto_map": { "AutoConfig": "ai4bharat/indictrans2-indic-en-1B--configuration_indictrans.IndicTransConfig", "AutoModelForSeq2SeqLM": "ai4bharat/indictrans2-indic-en-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": 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, "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": "4.44.2", "use_cache": true }