InfosysEnterprise/NT-Java-1.1B

1{2  "activation_function": "gelu_pytorch_tanh",3  "architectures": [4    "GPTBigCodeForCausalLM"5  ],6  "attention_softmax_in_fp32": true,7  "attn_pdrop": 0.1,8  "bos_token_id": 50256,9  "embd_pdrop": 0.1,10  "eos_token_id": 50256,11  "initializer_range": 0.02,12  "layer_norm_epsilon": 1e-05,13  "model_type": "gpt_bigcode",14  "multi_query": true,15  "n_embd": 2048,16  "n_head": 16,17  "n_inner": 8192,18  "n_layer": 24,19  "n_positions": 8192,20  "resid_pdrop": 0.1,21  "scale_attention_softmax_in_fp32": true,22  "scale_attn_weights": true,23  "summary_activation": null,24  "summary_first_dropout": 0.1,25  "summary_proj_to_labels": true,26  "summary_type": "cls_index",27  "summary_use_proj": true,28  "transformers_version": "4.39.2",29  "use_cache": true,30  "vocab_size": 4915231}32