CodeDevX/Vibe-Coding-Instruct

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": 104,
9  "dtype": "float32",
10  "embd_pdrop": 0.1,
11  "eos_token_id": 1,
12  "initializer_range": 0.02,
13  "layer_norm_epsilon": 1e-05,
14  "model_type": "gpt2",
15  "n_embd": 512,
16  "n_head": 8,
17  "n_inner": null,
18  "n_layer": 8,
19  "n_positions": 512,
20  "pad_token_id": 0,
21  "reorder_and_upcast_attn": false,
22  "resid_pdrop": 0.1,
23  "scale_attn_by_inverse_layer_idx": false,
24  "scale_attn_weights": true,
25  "summary_activation": null,
26  "summary_first_dropout": 0.1,
27  "summary_proj_to_labels": true,
28  "summary_type": "cls_index",
29  "summary_use_proj": true,
30  "tie_word_embeddings": true,
31  "transformers_version": "5.12.0",
32  "use_cache": false,
33  "vocab_size": 105
34}
35