distilgpt2
Browse files- config.json +12 -5
- generation_config.json +1 -1
- pytorch_model.bin +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -8,14 +9,20 @@
|
|
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": 128,
|
15 |
-
"n_embd":
|
16 |
-
"n_head":
|
17 |
"n_inner": null,
|
18 |
-
"n_layer":
|
19 |
"n_positions": 1024,
|
20 |
"reorder_and_upcast_attn": false,
|
21 |
"resid_pdrop": 0.1,
|
@@ -33,7 +40,7 @@
|
|
33 |
}
|
34 |
},
|
35 |
"torch_dtype": "float32",
|
36 |
-
"transformers_version": "4.
|
37 |
"use_cache": true,
|
38 |
"vocab_size": 10000
|
39 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilgpt2",
|
3 |
+
"_num_labels": 1,
|
4 |
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
6 |
"GPT2LMHeadModel"
|
|
|
9 |
"bos_token_id": 50256,
|
10 |
"embd_pdrop": 0.1,
|
11 |
"eos_token_id": 50256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
"layer_norm_epsilon": 1e-05,
|
20 |
"model_type": "gpt2",
|
21 |
"n_ctx": 128,
|
22 |
+
"n_embd": 768,
|
23 |
+
"n_head": 12,
|
24 |
"n_inner": null,
|
25 |
+
"n_layer": 6,
|
26 |
"n_positions": 1024,
|
27 |
"reorder_and_upcast_attn": false,
|
28 |
"resid_pdrop": 0.1,
|
|
|
40 |
}
|
41 |
},
|
42 |
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.28.1",
|
44 |
"use_cache": true,
|
45 |
"vocab_size": 10000
|
46 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.28.1"
|
6 |
}
|
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 sha256:6567f4b2908b6c908c3945749f4b190f39fb7e432107467934c91efc61653ea8
|
3 |
+
size 210299613
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
|
|
3 |
"eos_token": "</s>",
|
4 |
"model_max_length": 1000000000000000019884624838656,
|
5 |
"pad_token": "<pad>",
|
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
"eos_token": "</s>",
|
5 |
"model_max_length": 1000000000000000019884624838656,
|
6 |
"pad_token": "<pad>",
|
training_args.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:fc51561c5a41160be436bebb6dc349b3512b0cefa2fd91f7be111923a6aae848
|
3 |
+
size 3567
|