Yurii Paniv
commited on
Commit
•
b289fee
1
Parent(s):
2719cd2
Initial release
Browse files- README.md +2 -0
- added_tokens.json +1 -0
- config.json +45 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,3 +1,5 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: mit
|
3 |
---
|
|
|
1 |
---
|
2 |
+
tags:
|
3 |
+
- conversational
|
4 |
license: mit
|
5 |
---
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"[SEP]": 50257, "<pad>": 50258, "[CLS]": 50259, "[MASK]": 50260}
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Tereveni-AI/gpt2-124M-uk-fiction",
|
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 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"layer_norm_epsilon": 1e-05,
|
19 |
+
"model_type": "gpt2",
|
20 |
+
"n_ctx": 1024,
|
21 |
+
"n_embd": 768,
|
22 |
+
"n_head": 12,
|
23 |
+
"n_inner": null,
|
24 |
+
"n_layer": 12,
|
25 |
+
"n_positions": 1024,
|
26 |
+
"output_past": true,
|
27 |
+
"reorder_and_upcast_attn": false,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
30 |
+
"scale_attn_weights": true,
|
31 |
+
"summary_activation": null,
|
32 |
+
"summary_first_dropout": 0.1,
|
33 |
+
"summary_proj_to_labels": true,
|
34 |
+
"summary_type": "cls_index",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.18.0",
|
38 |
+
"use_cache": true,
|
39 |
+
"task_specific_params": {
|
40 |
+
"conversational": {
|
41 |
+
"max_length": 1000
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"vocab_size": 50261
|
45 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e4aab5e4178bfbbe9126ac3bee93cdbb36e14aec4193fd33f23f19ba413f635
|
3 |
+
size 510408809
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a91eafc946a78b8508b0b665c203661f251a8b1cb2156ac1b5095f9168a4dfdc
|
3 |
+
size 1463041
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": null, "name_or_path": "Tereveni-AI/gpt2-124M-uk-fiction", "tokenizer_class": "AlbertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1d2eb7a64f0f977ace7cefb7b0b4e1bb02c766bb75a101655c383c9b697a3ca
|
3 |
+
size 1327
|