hyper-accel/tiny-random-gpt_bigcode

1{2  "_attn_implementation_autoset": false,3  "_name_or_path": "bigcode/starcoder",4  "activation_function": "gelu",5  "architectures": [6    "GPTBigCodeForCausalLM"7  ],8  "attention_softmax_in_fp32": true,9  "attn_pdrop": 0.1,10  "bos_token_id": 0,11  "embd_pdrop": 0.1,12  "eos_token_id": 0,13  "inference_runner": 0,14  "initializer_range": 0.02,15  "layer_norm_epsilon": 1e-05,16  "max_batch_size": null,17  "max_sequence_length": null,18  "model_type": "gpt_bigcode",19  "multi_query": true,20  "n_embd": 512,21  "n_head": 4,22  "n_inner": 2048,23  "n_layer": 2,24  "n_positions": 8192,25  "pad_key_length": true,26  "pre_allocate_kv_cache": false,27  "resid_pdrop": 0.1,28  "scale_attention_softmax_in_fp32": true,29  "scale_attn_weights": true,30  "summary_activation": null,31  "summary_first_dropout": 0.1,32  "summary_proj_to_labels": true,33  "summary_type": "cls_index",34  "summary_use_proj": true,35  "torch_dtype": "float32",36  "transformers_version": "4.44.0",37  "use_cache": true,38  "validate_runner_input": true,39  "vocab_size": 4915240}41