Doron Adler
commited on
Commit
•
8754845
1
Parent(s):
85c5291
Norod78/hebrew-bad_wiki-gpt_neo-tiny
Browse files- added_tokens.json +1 -0
- config.json +46 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<|unknown|>": 50259, "<|startoftext|>": 50258, "<|endoftext|>": 50257}
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Norod78/hebrew-gpt_neo-tiny",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPTNeoForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"attention_layers": [
|
9 |
+
"global",
|
10 |
+
"global",
|
11 |
+
"global",
|
12 |
+
"global",
|
13 |
+
"global",
|
14 |
+
"global"
|
15 |
+
],
|
16 |
+
"attention_types": [
|
17 |
+
[
|
18 |
+
[
|
19 |
+
"global"
|
20 |
+
],
|
21 |
+
6
|
22 |
+
]
|
23 |
+
],
|
24 |
+
"bos_token_id": 50256,
|
25 |
+
"embed_dropout": 0.1,
|
26 |
+
"eos_token_id": 50256,
|
27 |
+
"gradient_checkpointing": false,
|
28 |
+
"hidden_size": 768,
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": null,
|
31 |
+
"layer_norm_epsilon": 1e-05,
|
32 |
+
"max_position_embeddings": 1024,
|
33 |
+
"model_type": "gpt_neo",
|
34 |
+
"num_heads": 12,
|
35 |
+
"num_layers": 6,
|
36 |
+
"resid_dropout": 0.1,
|
37 |
+
"summary_activation": null,
|
38 |
+
"summary_first_dropout": 0.1,
|
39 |
+
"summary_proj_to_labels": true,
|
40 |
+
"summary_type": "cls_index",
|
41 |
+
"summary_use_proj": true,
|
42 |
+
"transformers_version": "4.6.0",
|
43 |
+
"use_cache": true,
|
44 |
+
"vocab_size": 50257,
|
45 |
+
"window_size": 256
|
46 |
+
}
|
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:e61c5c5f8e9ff84ce8e637bc7f63f91b2a2caadc8e600713bf1ec2e8fb80fdf4
|
3 |
+
size 333917693
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<|startoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|unknown|>"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "do_lower_case": false, "max_len": 1024, "special_tokens_map_file": "special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "Norod78/hebrew-gpt_neo-tiny", "errors": "replace"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|