Update config.json
Browse files- config.json +2 -27
config.json
CHANGED
|
@@ -1,26 +1,14 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"GPT2LMHeadModel"
|
| 4 |
],
|
| 5 |
"attn_pdrop": 0.1,
|
| 6 |
-
"bos_token_id": null,
|
| 7 |
-
"do_sample": false,
|
| 8 |
"embd_pdrop": 0.1,
|
|
|
|
| 9 |
"eos_token_ids": null,
|
| 10 |
-
"finetuning_task": null,
|
| 11 |
-
"id2label": {
|
| 12 |
-
"0": "LABEL_0",
|
| 13 |
-
"1": "LABEL_1"
|
| 14 |
-
},
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
-
"is_decoder": false,
|
| 17 |
-
"label2id": {
|
| 18 |
-
"LABEL_0": 0,
|
| 19 |
-
"LABEL_1": 1
|
| 20 |
-
},
|
| 21 |
"layer_norm_epsilon": 1e-05,
|
| 22 |
-
"length_penalty": 1.0,
|
| 23 |
-
"max_length": 20,
|
| 24 |
"model_type": "gpt2",
|
| 25 |
"n_ctx": 1024,
|
| 26 |
"n_embd": 1024,
|
|
@@ -28,26 +16,13 @@
|
|
| 28 |
"n_layer": 24,
|
| 29 |
"n_positions": 1024,
|
| 30 |
"n_special": 0,
|
| 31 |
-
"num_beams": 1,
|
| 32 |
-
"num_labels": 2,
|
| 33 |
-
"num_return_sequences": 1,
|
| 34 |
-
"output_attentions": false,
|
| 35 |
-
"output_hidden_states": false,
|
| 36 |
"output_past": true,
|
| 37 |
-
"pad_token_id": null,
|
| 38 |
"predict_special_tokens": true,
|
| 39 |
-
"pruned_heads": {},
|
| 40 |
-
"repetition_penalty": 1.0,
|
| 41 |
"resid_pdrop": 0.1,
|
| 42 |
"summary_activation": null,
|
| 43 |
"summary_first_dropout": 0.1,
|
| 44 |
"summary_proj_to_labels": true,
|
| 45 |
"summary_type": "cls_index",
|
| 46 |
"summary_use_proj": true,
|
| 47 |
-
"temperature": 1.0,
|
| 48 |
-
"top_k": 50,
|
| 49 |
-
"top_p": 1.0,
|
| 50 |
-
"torchscript": false,
|
| 51 |
-
"use_bfloat16": false,
|
| 52 |
"vocab_size": 50257
|
| 53 |
}
|
| 1 |
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
"architectures": [
|
| 4 |
"GPT2LMHeadModel"
|
| 5 |
],
|
| 6 |
"attn_pdrop": 0.1,
|
|
|
|
|
|
|
| 7 |
"embd_pdrop": 0.1,
|
| 8 |
+
"eos_token_id": 50256,
|
| 9 |
"eos_token_ids": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"layer_norm_epsilon": 1e-05,
|
|
|
|
|
|
|
| 12 |
"model_type": "gpt2",
|
| 13 |
"n_ctx": 1024,
|
| 14 |
"n_embd": 1024,
|
| 16 |
"n_layer": 24,
|
| 17 |
"n_positions": 1024,
|
| 18 |
"n_special": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
"output_past": true,
|
|
|
|
| 20 |
"predict_special_tokens": true,
|
|
|
|
|
|
|
| 21 |
"resid_pdrop": 0.1,
|
| 22 |
"summary_activation": null,
|
| 23 |
"summary_first_dropout": 0.1,
|
| 24 |
"summary_proj_to_labels": true,
|
| 25 |
"summary_type": "cls_index",
|
| 26 |
"summary_use_proj": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"vocab_size": 50257
|
| 28 |
}
|