Hello, persian gpt2
Browse files- README.md +29 -0
- added_tokens.json +1 -0
- config.json +37 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +29 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: fa
|
3 |
+
license: apache-2.0
|
4 |
+
widget:
|
5 |
+
- text: "در یک اتفاق شگفت انگیز، پژوهشگران"
|
6 |
+
- text: "گرفتگی بینی در کودکان و بهخصوص نوزادان باعث میشود"
|
7 |
+
- text: "امیدواریم نوروز امسال سالی"
|
8 |
+
---
|
9 |
+
|
10 |
+
# ParsGPT2
|
11 |
+
|
12 |
+
|
13 |
+
### BibTeX entry and citation info
|
14 |
+
|
15 |
+
Please cite in publications as the following:
|
16 |
+
|
17 |
+
```bibtex
|
18 |
+
@misc{ParsGPT2,
|
19 |
+
author = {Hooshvare Team},
|
20 |
+
title = {ParsGPT2 the Persian version of GPT2},
|
21 |
+
year = {2021},
|
22 |
+
publisher = {GitHub},
|
23 |
+
journal = {GitHub repository},
|
24 |
+
howpublished = {\url{https://github.com/hooshvare/parsgpt}},
|
25 |
+
}
|
26 |
+
```
|
27 |
+
|
28 |
+
## Questions?
|
29 |
+
Post a Github issue on the [ParsGPT2 Issues](https://github.com/hooshvare/parsgpt/issues) repo.
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"[N]": 42000}
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 5,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 5,
|
10 |
+
"gradient_checkpointing": false,
|
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 |
+
"resid_pdrop": 0.1,
|
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 |
+
"task_specific_params": {
|
27 |
+
"text-generation": {
|
28 |
+
"do_sample": true,
|
29 |
+
"max_length": 50,
|
30 |
+
"top_k": 50,
|
31 |
+
"top_p": 0.95
|
32 |
+
}
|
33 |
+
},
|
34 |
+
"transformers_version": "4.2.1",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 42001
|
37 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46b0b806c740a0f0a9f056f5574c5fa896166fe844945fd3c849bf34365e5060
|
3 |
+
size 485044198
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b8af318c7dcde1cd1b86aad51b8a5b47c7b6b35b6db40c18378577a6bfe33bf
|
3 |
+
size 472571216
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"unk_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"single_word": false,
|
5 |
+
"lstrip": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"__type": "AddedToken"
|
9 |
+
},
|
10 |
+
"bos_token": {
|
11 |
+
"content": "<|endoftext|>",
|
12 |
+
"single_word": false,
|
13 |
+
"lstrip": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"__type": "AddedToken"
|
17 |
+
},
|
18 |
+
"eos_token": {
|
19 |
+
"content": "<|endoftext|>",
|
20 |
+
"single_word": false,
|
21 |
+
"lstrip": false,
|
22 |
+
"rstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"__type": "AddedToken"
|
25 |
+
},
|
26 |
+
"add_prefix_space": false,
|
27 |
+
"special_tokens_map_file": null,
|
28 |
+
"errors": "replace"
|
29 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|