AlexBlin/software-engineering-model

1{2  "activation_function": "gelu_new",3  "add_cross_attention": false,4  "architectures": [5    "GPT2LMHeadModel"6  ],7  "attn_pdrop": 0.1,8  "bos_token_id": 1,9  "dtype": "float32",10  "embd_pdrop": 0.1,11  "eos_token_id": 2,12  "gradient_checkpointing": false,13  "id2label": {14    "0": "LABEL_0"15  },16  "initializer_range": 0.02,17  "label2id": {18    "LABEL_0": 019  },20  "layer_norm_epsilon": 1e-05,21  "model_type": "gpt2",22  "n_ctx": 2048,23  "n_embd": 768,24  "n_head": 12,25  "n_inner": null,26  "n_layer": 12,27  "n_positions": 2048,28  "pad_token_id": 0,29  "reorder_and_upcast_attn": false,30  "resid_pdrop": 0.1,31  "scale_attn_by_inverse_layer_idx": false,32  "scale_attn_weights": true,33  "summary_activation": null,34  "summary_first_dropout": 0.1,35  "summary_proj_to_labels": true,36  "summary_type": "cls_index",37  "summary_use_proj": true,38  "tie_word_embeddings": true,39  "transformers_version": "5.10.2",40  "use_cache": false,41  "vocab_size": 5026442}43