Upload 9 files
Browse files- added_tokens.json +2 -3
- config.json +3 -3
- generation_config.json +1 -1
- pytorch_model.bin +2 -2
- special_tokens_map.json +16 -0
- tokenizer.json +32 -2
- tokenizer_config.json +33 -24
added_tokens.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"<|
|
3 |
-
"<|
|
4 |
-
"<|user|>": 50258
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"<|SYSTEM|>": 50258,
|
3 |
+
"<|USER|>": 50257
|
|
|
4 |
}
|
config.json
CHANGED
@@ -17,7 +17,7 @@
|
|
17 |
"n_inner": null,
|
18 |
"n_layer": 12,
|
19 |
"n_positions": 1024,
|
20 |
-
"
|
21 |
"reorder_and_upcast_attn": false,
|
22 |
"resid_pdrop": 0.1,
|
23 |
"scale_attn_by_inverse_layer_idx": false,
|
@@ -33,7 +33,7 @@
|
|
33 |
}
|
34 |
},
|
35 |
"torch_dtype": "float32",
|
36 |
-
"transformers_version": "4.
|
37 |
"use_cache": true,
|
38 |
-
"vocab_size":
|
39 |
}
|
|
|
17 |
"n_inner": null,
|
18 |
"n_layer": 12,
|
19 |
"n_positions": 1024,
|
20 |
+
"output_hidden_states": true,
|
21 |
"reorder_and_upcast_attn": false,
|
22 |
"resid_pdrop": 0.1,
|
23 |
"scale_attn_by_inverse_layer_idx": false,
|
|
|
33 |
}
|
34 |
},
|
35 |
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.36.2",
|
37 |
"use_cache": true,
|
38 |
+
"vocab_size": 50259
|
39 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.36.2"
|
6 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c4c3f16e58ea48a7474e93459ccd58a09f0808a18d14550d55dadf06aeef79c
|
3 |
+
size 497813850
|
special_tokens_map.json
CHANGED
@@ -1,4 +1,20 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<|endoftext|>",
|
4 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<|USER|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<|SYSTEM|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
],
|
18 |
"bos_token": {
|
19 |
"content": "<|endoftext|>",
|
20 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -1,7 +1,19 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 50256,
|
@@ -11,6 +23,24 @@
|
|
11 |
"rstrip": false,
|
12 |
"normalized": true,
|
13 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
}
|
15 |
],
|
16 |
"normalizer": null,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 1024,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": "BatchLongest",
|
11 |
+
"direction": "Right",
|
12 |
+
"pad_to_multiple_of": null,
|
13 |
+
"pad_id": 50256,
|
14 |
+
"pad_type_id": 0,
|
15 |
+
"pad_token": "<|endoftext|>"
|
16 |
+
},
|
17 |
"added_tokens": [
|
18 |
{
|
19 |
"id": 50256,
|
|
|
23 |
"rstrip": false,
|
24 |
"normalized": true,
|
25 |
"special": true
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"id": 50257,
|
29 |
+
"content": "<|USER|>",
|
30 |
+
"single_word": false,
|
31 |
+
"lstrip": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"id": 50258,
|
38 |
+
"content": "<|SYSTEM|>",
|
39 |
+
"single_word": false,
|
40 |
+
"lstrip": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"normalized": false,
|
43 |
+
"special": true
|
44 |
}
|
45 |
],
|
46 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -1,33 +1,42 @@
|
|
1 |
{
|
2 |
"add_bos_token": false,
|
3 |
"add_prefix_space": false,
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
},
|
|
|
|
|
|
|
|
|
|
|
12 |
"clean_up_tokenization_spaces": true,
|
13 |
-
"eos_token":
|
14 |
-
"__type": "AddedToken",
|
15 |
-
"content": "<|endoftext|>",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": true,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false
|
20 |
-
},
|
21 |
"errors": "replace",
|
22 |
"model_max_length": 1024,
|
23 |
-
"pad_token":
|
24 |
"tokenizer_class": "GPT2Tokenizer",
|
25 |
-
"unk_token":
|
26 |
-
"__type": "AddedToken",
|
27 |
-
"content": "<|endoftext|>",
|
28 |
-
"lstrip": false,
|
29 |
-
"normalized": true,
|
30 |
-
"rstrip": false,
|
31 |
-
"single_word": false
|
32 |
-
}
|
33 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": false,
|
3 |
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"50257": {
|
14 |
+
"content": "<|USER|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"50258": {
|
22 |
+
"content": "<|SYSTEM|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<|USER|>",
|
32 |
+
"<|SYSTEM|>"
|
33 |
+
],
|
34 |
+
"bos_token": "<|endoftext|>",
|
35 |
"clean_up_tokenization_spaces": true,
|
36 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
"errors": "replace",
|
38 |
"model_max_length": 1024,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
"tokenizer_class": "GPT2Tokenizer",
|
41 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
}
|