upload model
Browse files- config.json +29 -0
- pytorch_model.bin +3 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_fast",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"embd_pdrop": 0.1,
|
8 |
+
"initializer_range": 0.02,
|
9 |
+
"layer_norm_epsilon": 1e-05,
|
10 |
+
"model_type": "gpt2",
|
11 |
+
"n_ctx": 1024,
|
12 |
+
"n_embd": 768,
|
13 |
+
"n_head": 12,
|
14 |
+
"n_inner": 3072,
|
15 |
+
"n_layer": 12,
|
16 |
+
"n_positions": 1024,
|
17 |
+
"reorder_and_upcast_attn": false,
|
18 |
+
"resid_pdrop": 0.1,
|
19 |
+
"scale_attn_by_inverse_layer_idx": false,
|
20 |
+
"scale_attn_weights": true,
|
21 |
+
"summary_activation": null,
|
22 |
+
"summary_first_dropout": 0.1,
|
23 |
+
"summary_proj_to_labels": true,
|
24 |
+
"summary_type": "cls_index",
|
25 |
+
"summary_use_proj": true,
|
26 |
+
"transformers_version": "4.12.3",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 21133
|
29 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ece4a0b8cd29cdcc2c84211ec7c3409a05e050d37a71928549dd63bfe380ae2f
|
3 |
+
size 420927593
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"cls_token": "<|beginoftext|>", "sep_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|