defog/sqlcoder2

1{2  "_name_or_path": "bigcode/starcoder",3  "activation_function": "gelu",4  "architectures": [5    "GPTBigCodeForCausalLM"6  ],7  "attention_softmax_in_fp32": true,8  "attn_pdrop": 0.1,9  "bos_token_id": 0,10  "embd_pdrop": 0.1,11  "eos_token_id": 0,12  "inference_runner": 0,13  "initializer_range": 0.02,14  "layer_norm_epsilon": 1e-05,15  "max_batch_size": null,16  "max_sequence_length": null,17  "model_type": "gpt_bigcode",18  "multi_query": true,19  "n_embd": 6144,20  "n_head": 48,21  "n_inner": 24576,22  "n_layer": 40,23  "n_positions": 8192,24  "pad_key_length": true,25  "pre_allocate_kv_cache": false,26  "resid_pdrop": 0.1,27  "scale_attention_softmax_in_fp32": true,28  "scale_attn_weights": true,29  "summary_activation": null,30  "summary_first_dropout": 0.1,31  "summary_proj_to_labels": true,32  "summary_type": "cls_index",33  "summary_use_proj": true,34  "torch_dtype": "float16",35  "transformers_version": "4.34.0",36  "use_cache": true,37  "validate_runner_input": true,38  "vocab_size": 4915239}40