Upload folder using huggingface_hub
Browse files- config.json +8 -2
- generation_config.json +4 -0
- merges.txt +0 -0
- model.safetensors +2 -2
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -0
- vocab.json +0 -0
config.json
CHANGED
@@ -1,8 +1,14 @@
|
|
1 |
{
|
|
|
|
|
|
|
2 |
"block_size": 512,
|
3 |
"d_model": 768,
|
4 |
-
"dropout": 0.
|
|
|
5 |
"n_heads": 12,
|
6 |
"n_layers": 12,
|
|
|
|
|
7 |
"vocab_size": 50257
|
8 |
-
}
|
|
|
1 |
{
|
2 |
+
"architectures": [
|
3 |
+
"GPT"
|
4 |
+
],
|
5 |
"block_size": 512,
|
6 |
"d_model": 768,
|
7 |
+
"dropout": 0.0,
|
8 |
+
"model_type": "gpt",
|
9 |
"n_heads": 12,
|
10 |
"n_layers": 12,
|
11 |
+
"torch_dtype": "float32",
|
12 |
+
"transformers_version": "4.42.3",
|
13 |
"vocab_size": 50257
|
14 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.42.3"
|
4 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
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:c97918a726d323439e0d7523f5451794d2591d1c6184b2d2ed9609d6b5ced773
|
3 |
+
size 650595592
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"clean_up_tokenization_spaces": true,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"model_max_length": 1024,
|
17 |
+
"tokenizer_class": "GPT2Tokenizer",
|
18 |
+
"unk_token": "<|endoftext|>"
|
19 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|