Upload 8 files
Browse files- .gitattributes +1 -2
- config.json +27 -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
.gitattributes
CHANGED
@@ -7,7 +7,6 @@
|
|
7 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
8 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
9 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
10 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
11 |
*.model filter=lfs diff=lfs merge=lfs -text
|
12 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
13 |
*.npy filter=lfs diff=lfs merge=lfs -text
|
@@ -28,5 +27,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
28 |
*.wasm filter=lfs diff=lfs merge=lfs -text
|
29 |
*.xz filter=lfs diff=lfs merge=lfs -text
|
30 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
31 |
-
*.
|
32 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
7 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
8 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
9 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
|
|
10 |
*.model filter=lfs diff=lfs merge=lfs -text
|
11 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
12 |
*.npy filter=lfs diff=lfs merge=lfs -text
|
|
|
27 |
*.wasm filter=lfs diff=lfs merge=lfs -text
|
28 |
*.xz filter=lfs diff=lfs merge=lfs -text
|
29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/jupyter/lm/500g/meaningshift/models/2022-Q1-15M/checkpoint-78564/",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.13.0.dev0",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
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 sha256:34d66f79c87a959ed32b1e49ee4a5b342d8b2c840aa1709b7699bd04319e99f9
|
3 |
+
size 498875371
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
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": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/home/jupyter/lm/500g/meaningshift/models/2022-Q1-15M/checkpoint-78564/", "tokenizer_class": "RobertaTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|