reciprocate
commited on
Commit
·
2dabdda
1
Parent(s):
1082059
1M
Browse files- config.json +31 -0
- merges.txt +1 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +17 -0
- tokenizer_config.json +32 -0
- vocab.json +24 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 50256,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 50256,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"layer_norm_epsilon": 1e-05,
|
12 |
+
"model_type": "gpt2",
|
13 |
+
"n_embd": 144,
|
14 |
+
"n_head": 6,
|
15 |
+
"n_inner": null,
|
16 |
+
"n_layer": 6,
|
17 |
+
"n_positions": 1024,
|
18 |
+
"reorder_and_upcast_attn": false,
|
19 |
+
"resid_pdrop": 0.1,
|
20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
21 |
+
"scale_attn_weights": true,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.21.2",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 23
|
31 |
+
}
|
merges.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
#version: 0.2
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d7e61e1197321c4ce6ab7856d100a6173d45c318bee444f4718822f5c0f558b
|
3 |
+
size 12939805
|
special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": "<|endoftext|>",
|
10 |
+
"unk_token": {
|
11 |
+
"content": "<|endoftext|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"model_max_len": 1024,
|
22 |
+
"pad_token": null,
|
23 |
+
"tokenizer_class": "GPT2Tokenizer",
|
24 |
+
"unk_token": {
|
25 |
+
"__type": "AddedToken",
|
26 |
+
"content": "<|endoftext|>",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": true,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
}
|
32 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"a": 0,
|
3 |
+
"b": 1,
|
4 |
+
"c": 2,
|
5 |
+
"d": 3,
|
6 |
+
"e": 4,
|
7 |
+
"f": 5,
|
8 |
+
"g": 6,
|
9 |
+
"h": 7,
|
10 |
+
"i": 8,
|
11 |
+
"j": 9,
|
12 |
+
"k": 10,
|
13 |
+
"l": 11,
|
14 |
+
"m": 12,
|
15 |
+
"n": 13,
|
16 |
+
"o": 14,
|
17 |
+
"p": 15,
|
18 |
+
"q": 16,
|
19 |
+
"r": 17,
|
20 |
+
"s": 18,
|
21 |
+
"t": 19,
|
22 |
+
"u": 20,
|
23 |
+
"|": 21
|
24 |
+
}
|