bigcode/gpt_bigcode-santacoder

1{2  "activation_function": "gelu_pytorch_tanh",3  "architectures": [4    "GPTBigCodeForCausalLM"5  ],6  "attention_softmax_in_fp32": true,7  "multi_query": true,8  "attn_pdrop": 0.1,9  "bos_token_id": 49152,10  "embd_pdrop": 0.1,11  "eos_token_id": 49152,12  "initializer_range": 0.02,13  "layer_norm_epsilon": 1e-05,14  "model_type": "gpt_bigcode",15  "n_embd": 2048,16  "n_head": 16,17  "n_inner": 8192,18  "n_layer": 24,19  "n_positions": 2048,20  "resid_pdrop": 0.1,21  "runner_max_sequence_length": null,22  "scale_attention_softmax_in_fp32": true,23  "scale_attn_weights": true,24  "summary_activation": null,25  "summary_first_dropout": 0.1,26  "summary_proj_to_labels": true,27  "summary_type": "cls_index",28  "summary_use_proj": true,29  "transformers_version": "4.28.0.dev0",30  "use_cache": true,31  "vocab_size": 4928032}33