{ "vocab_size": 16000, "hidden_size": 768, "num_hidden_layers": 12, "num_attention_heads": 16, "intermediate_size": 3072, "hidden_dropout_prob": 0.1, "attention_probs_dropout_prob": 0.1, "max_position_embeddings": 512, "layer_norm_eps": 1e-12, "pad_token_id": 0, "bos_token_id": 1, "eos_token_id": 2, "tie_word_embeddings": true, "hidden_act": "silu", "normalization_layer": "rmsnorm", "positional_encoding_type": "rope", "unk_token_id": 3, "architectures": [ "HindiCausalLM" ], "model_type": "hindi_causal_lm" }