|
{ |
|
"_name_or_path": "ai4bharat/indictrans2-indic-en-dist-200M", |
|
"activation_dropout": 0.0, |
|
"activation_function": "gelu", |
|
"architectures": [ |
|
"IndicTransForConditionalGeneration" |
|
], |
|
"auto_map": { |
|
"AutoConfig": "configuration_indictrans.IndicTransConfig", |
|
"AutoModelForSeq2SeqLM": "modeling_indictrans.IndicTransForConditionalGeneration" |
|
}, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 0, |
|
"decoder_attention_heads": 8, |
|
"decoder_embed_dim": 512, |
|
"decoder_ffn_dim": 2048, |
|
"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": 8, |
|
"encoder_embed_dim": 512, |
|
"encoder_ffn_dim": 2048, |
|
"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": true, |
|
"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": true, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.33.1", |
|
"use_cache": true |
|
} |
|
|