optimum-intel-internal-testing/tiny-random-GPTBigCodeModel

1{2  "activation_function": "relu",3  "architectures": [4    "GPTBigCodeModel"5  ],6  "attention_softmax_in_fp32": false,7  "attn_pdrop": 0.1,8  "bos_token_id": 0,9  "embd_pdrop": 0.1,10  "eos_token_id": 0,11  "gradient_checkpointing": false,12  "initializer_range": 0.02,13  "layer_norm_epsilon": 1e-05,14  "model_type": "gpt_bigcode",15  "multi_query": true,16  "n_embd": 32,17  "n_head": 4,18  "n_inner": 37,19  "n_layer": 5,20  "n_positions": 512,21  "pad_token_id": 1021,22  "reorder_and_upcast_attn": false,23  "resid_pdrop": 0.1,24  "scale_attention_softmax_in_fp32": false,25  "scale_attn_by_inverse_layer_idx": false,26  "scale_attn_weights": true,27  "torch_dtype": "float32",28  "transformers_version": "4.28.0.dev0",29  "type_vocab_size": 16,30  "use_cache": true,31  "vocab_size": 102432}33