MrAnderson
commited on
Commit
•
f7a90cb
1
Parent(s):
91478c1
Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +30 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "uw-madison/nystromformer-512",
|
3 |
+
"architectures": [
|
4 |
+
"NystromformerForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"conv_kernel_size": 65,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu_new",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"inv_coeff_init_option": false,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 1024,
|
18 |
+
"model_type": "nystromformer",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"num_landmarks": 64,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"segment_means_seq_len": 64,
|
24 |
+
"tokenizer_class": "AlbertTokenizer",
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.17.0",
|
27 |
+
"type_vocab_size": 2,
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 30000
|
30 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:174abf04415d645f9ad8abcc611131b2beea9674d9714f85be6e01333abf8147
|
3 |
+
size 435682457
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "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 sha256:39ee5d0cd20ab9616138d90a6d9c811ed41aba04a95d515bee6d4d5cd42ef0a6
|
3 |
+
size 761089
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "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": "C:\\Users\\prana/.cache\\huggingface\\transformers\\d225353999b4547543d7b66be9304faa64950fec7fb25e2d220dd84ee3f8b991.15ed5b79b197b4fcc5f3f80b2ee89a5a3ad708dbd076575cd22cffd9e1a56284", "name_or_path": "uw-madison/nystromformer-512", "tokenizer_class": "AlbertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7496fba9672cffff5e3a6aa54a536d42a3cad60cec2575f5ed4a1b9dd139cda8
|
3 |
+
size 3183
|