arunprsh
commited on
Commit
·
56a46aa
1
Parent(s):
aecd46e
Adding model artifacts
Browse files- .ipynb_checkpoints/generation_config-checkpoint.json +6 -0
- added_tokens.json +7 -0
- config.json +2 -2
- generation_config.json +6 -0
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +34 -0
- training_args.bin +0 -3
- vocab.json +0 -0
.ipynb_checkpoints/generation_config-checkpoint.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.26.1"
|
6 |
+
}
|
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|mask|>": 50261,
|
3 |
+
"<|pad|>": 50260,
|
4 |
+
"<|speaker-1|>": 50258,
|
5 |
+
"<|speaker-2|>": 50259,
|
6 |
+
"<|startoftext|>": 50257
|
7 |
+
}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPTNeoForCausalLM"
|
@@ -47,7 +47,7 @@
|
|
47 |
"summary_type": "cls_index",
|
48 |
"summary_use_proj": true,
|
49 |
"torch_dtype": "float32",
|
50 |
-
"transformers_version": "4.
|
51 |
"use_cache": true,
|
52 |
"vocab_size": 50262,
|
53 |
"window_size": 256
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./../02-train/model",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPTNeoForCausalLM"
|
|
|
47 |
"summary_type": "cls_index",
|
48 |
"summary_use_proj": true,
|
49 |
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.26.1",
|
51 |
"use_cache": true,
|
52 |
"vocab_size": 50262,
|
53 |
"window_size": 256
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.26.1"
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 sha256:42c7bf8a768d75f034b0996fcbb79c548cd8147c47c6456e0944970abfce9498
|
3 |
+
size 551197905
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|speaker-1|>",
|
4 |
+
"<|speaker-2|>",
|
5 |
+
"<|pad|>",
|
6 |
+
"<|mask|>"
|
7 |
+
],
|
8 |
+
"bos_token": "<|startoftext|>",
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_length": 2048,
|
22 |
+
"name_or_path": "./tokenizer",
|
23 |
+
"pad_token": null,
|
24 |
+
"special_tokens_map_file": null,
|
25 |
+
"tokenizer_class": "GPT2Tokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:6767ce684cbf6fdd4f2fd9fa4b3b1322d725db6bd8f975709b3debe164676427
|
3 |
-
size 3247
|
|
|
|
|
|
|
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|