onnx/config.json
879 B · 39 lines · json Raw
1 {
2 "_name_or_path": "gpt2",
3 "activation_function": "gelu_new",
4 "architectures": [
5 "GPT2LMHeadModel"
6 ],
7 "attn_pdrop": 0.1,
8 "bos_token_id": 50256,
9 "embd_pdrop": 0.1,
10 "eos_token_id": 50256,
11 "initializer_range": 0.02,
12 "layer_norm_epsilon": 1e-05,
13 "model_type": "gpt2",
14 "n_ctx": 1024,
15 "n_embd": 768,
16 "n_head": 12,
17 "n_inner": null,
18 "n_layer": 12,
19 "n_positions": 1024,
20 "reorder_and_upcast_attn": false,
21 "resid_pdrop": 0.1,
22 "scale_attn_by_inverse_layer_idx": false,
23 "scale_attn_weights": true,
24 "summary_activation": null,
25 "summary_first_dropout": 0.1,
26 "summary_proj_to_labels": true,
27 "summary_type": "cls_index",
28 "summary_use_proj": true,
29 "task_specific_params": {
30 "text-generation": {
31 "do_sample": true,
32 "max_length": 50
33 }
34 },
35 "transformers_version": "4.30.2",
36 "use_cache": true,
37 "vocab_size": 50257
38 }
39