Update config.json
Browse files- config.json +0 -24
config.json
CHANGED
|
@@ -6,52 +6,28 @@
|
|
| 6 |
],
|
| 7 |
"attn_pdrop": 0.1,
|
| 8 |
"bos_token_id": 50256,
|
| 9 |
-
"decoder_start_token_id": null,
|
| 10 |
-
"do_sample": false,
|
| 11 |
-
"early_stopping": false,
|
| 12 |
"embd_pdrop": 0.1,
|
| 13 |
"eos_token_id": 50256,
|
| 14 |
-
"finetuning_task": null,
|
| 15 |
"id2label": {
|
| 16 |
"0": "LABEL_0"
|
| 17 |
},
|
| 18 |
"initializer_range": 0.02,
|
| 19 |
-
"is_decoder": false,
|
| 20 |
-
"is_encoder_decoder": false,
|
| 21 |
"label2id": {
|
| 22 |
"LABEL_0": 0
|
| 23 |
},
|
| 24 |
"layer_norm_epsilon": 1e-05,
|
| 25 |
-
"length_penalty": 1.0,
|
| 26 |
-
"max_length": 20,
|
| 27 |
-
"min_length": 0,
|
| 28 |
"model_type": "gpt2",
|
| 29 |
"n_ctx": 1024,
|
| 30 |
"n_embd": 768,
|
| 31 |
"n_head": 12,
|
| 32 |
"n_layer": 12,
|
| 33 |
"n_positions": 1024,
|
| 34 |
-
"no_repeat_ngram_size": 0,
|
| 35 |
-
"num_beams": 1,
|
| 36 |
-
"num_return_sequences": 1,
|
| 37 |
-
"output_attentions": false,
|
| 38 |
-
"output_hidden_states": false,
|
| 39 |
"output_past": true,
|
| 40 |
-
"pad_token_id": null,
|
| 41 |
-
"prefix": null,
|
| 42 |
-
"pruned_heads": {},
|
| 43 |
-
"repetition_penalty": 1.0,
|
| 44 |
"resid_pdrop": 0.1,
|
| 45 |
"summary_activation": null,
|
| 46 |
"summary_first_dropout": 0.1,
|
| 47 |
"summary_proj_to_labels": true,
|
| 48 |
"summary_type": "cls_index",
|
| 49 |
"summary_use_proj": true,
|
| 50 |
-
"task_specific_params": null,
|
| 51 |
-
"temperature": 1.0,
|
| 52 |
-
"top_k": 50,
|
| 53 |
-
"top_p": 1.0,
|
| 54 |
-
"torchscript": false,
|
| 55 |
-
"use_bfloat16": false,
|
| 56 |
"vocab_size": 50257
|
| 57 |
}
|
| 6 |
],
|
| 7 |
"attn_pdrop": 0.1,
|
| 8 |
"bos_token_id": 50256,
|
|
|
|
|
|
|
|
|
|
| 9 |
"embd_pdrop": 0.1,
|
| 10 |
"eos_token_id": 50256,
|
|
|
|
| 11 |
"id2label": {
|
| 12 |
"0": "LABEL_0"
|
| 13 |
},
|
| 14 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
| 15 |
"label2id": {
|
| 16 |
"LABEL_0": 0
|
| 17 |
},
|
| 18 |
"layer_norm_epsilon": 1e-05,
|
|
|
|
|
|
|
|
|
|
| 19 |
"model_type": "gpt2",
|
| 20 |
"n_ctx": 1024,
|
| 21 |
"n_embd": 768,
|
| 22 |
"n_head": 12,
|
| 23 |
"n_layer": 12,
|
| 24 |
"n_positions": 1024,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
"output_past": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"resid_pdrop": 0.1,
|
| 27 |
"summary_activation": null,
|
| 28 |
"summary_first_dropout": 0.1,
|
| 29 |
"summary_proj_to_labels": true,
|
| 30 |
"summary_type": "cls_index",
|
| 31 |
"summary_use_proj": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"vocab_size": 50257
|
| 33 |
}
|