Commit
•
1b190c9
1
Parent(s):
a5a4585
Upload model
Browse files- config.json +30 -32
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,41 +1,39 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"hidden_dropout_prob": 0.1,
|
| 11 |
-
"hidden_size": 768,
|
| 12 |
-
"id2label": {
|
| 13 |
-
"0": "LABEL_0",
|
| 14 |
-
"1": "LABEL_1",
|
| 15 |
-
"2": "LABEL_2",
|
| 16 |
-
"3": "LABEL_3",
|
| 17 |
-
"4": "LABEL_4"
|
| 18 |
-
},
|
| 19 |
"initializer_range": 0.02,
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
},
|
| 28 |
-
"layer_norm_eps": 1e-12,
|
| 29 |
-
"max_position_embeddings": 512,
|
| 30 |
-
"model_type": "bert",
|
| 31 |
-
"num_attention_heads": 12,
|
| 32 |
-
"num_hidden_layers": 12,
|
| 33 |
-
"pad_token_id": 0,
|
| 34 |
-
"position_embedding_type": "absolute",
|
| 35 |
-
"problem_type": "single_label_classification",
|
| 36 |
"torch_dtype": "float32",
|
| 37 |
"transformers_version": "4.28.1",
|
| 38 |
-
"type_vocab_size": 2,
|
| 39 |
"use_cache": true,
|
| 40 |
-
"vocab_size":
|
| 41 |
}
|
|
|
|
| 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 |
"torch_dtype": "float32",
|
| 36 |
"transformers_version": "4.28.1",
|
|
|
|
| 37 |
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93b783dbfbdfe4cb37d7dd5ae5ed476a1880ae866edb355a59477cc66860f316
|
| 3 |
+
size 510395581
|