Must Erhang
commited on
Commit
•
6c2e696
1
Parent(s):
186b138
Gpt2 Elite pretrained
Browse files- README.md +6 -0
- config.json +31 -0
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
- vocab.json +0 -0
README.md
CHANGED
@@ -1,3 +1,9 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
tags:
|
6 |
+
- gpt2
|
7 |
+
- transformer
|
8 |
+
- pre-training
|
9 |
---
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 50256,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 50256,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"layer_norm_epsilon": 1e-05,
|
12 |
+
"model_type": "gpt2",
|
13 |
+
"n_ctx": 1024,
|
14 |
+
"n_embd": 768,
|
15 |
+
"n_head": 12,
|
16 |
+
"n_layer": 12,
|
17 |
+
"n_positions": 1024,
|
18 |
+
"resid_pdrop": 0.1,
|
19 |
+
"summary_activation": null,
|
20 |
+
"summary_first_dropout": 0.1,
|
21 |
+
"summary_proj_to_labels": true,
|
22 |
+
"summary_type": "cls_index",
|
23 |
+
"summary_use_proj": true,
|
24 |
+
"task_specific_params": {
|
25 |
+
"text-generation": {
|
26 |
+
"do_sample": true,
|
27 |
+
"max_length": 50
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"vocab_size": 50257
|
31 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:618d3604575dd7d5a47d5157917c19a445f2c4bccc4776680b382c20f2e0146b
|
3 |
+
size 548144461
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|