Initial commit updates
Browse files- added_tokens.json +1 -0
- config.json +7 -2
- merges.txt +0 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<|startoftext|>": 50257, "<|pad|>": 50258}
|
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"_num_labels": 1,
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
@@ -8,6 +9,7 @@
|
|
8 |
"bos_token_id": 50256,
|
9 |
"embd_pdrop": 0.1,
|
10 |
"eos_token_id": 50256,
|
|
|
11 |
"id2label": {
|
12 |
"0": "LABEL_0"
|
13 |
},
|
@@ -20,6 +22,7 @@
|
|
20 |
"n_ctx": 1024,
|
21 |
"n_embd": 768,
|
22 |
"n_head": 12,
|
|
|
23 |
"n_layer": 6,
|
24 |
"n_positions": 1024,
|
25 |
"resid_pdrop": 0.1,
|
@@ -34,5 +37,7 @@
|
|
34 |
"max_length": 50
|
35 |
}
|
36 |
},
|
37 |
-
"
|
38 |
-
|
|
|
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilgpt2",
|
3 |
"_num_labels": 1,
|
4 |
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
|
|
9 |
"bos_token_id": 50256,
|
10 |
"embd_pdrop": 0.1,
|
11 |
"eos_token_id": 50256,
|
12 |
+
"gradient_checkpointing": false,
|
13 |
"id2label": {
|
14 |
"0": "LABEL_0"
|
15 |
},
|
|
|
22 |
"n_ctx": 1024,
|
23 |
"n_embd": 768,
|
24 |
"n_head": 12,
|
25 |
+
"n_inner": null,
|
26 |
"n_layer": 6,
|
27 |
"n_positions": 1024,
|
28 |
"resid_pdrop": 0.1,
|
|
|
37 |
"max_length": 50
|
38 |
}
|
39 |
},
|
40 |
+
"transformers_version": "4.4.2",
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 50259
|
43 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|pad|>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "pad_token": "<|pad|>", "model_max_length": 1024, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/accb287b5a5396b2597382916b6cc939fdab1366e89475a92338d3971b3d02b7.cf2d0ecb83b6df91b3dbb53f1d1e4c311578bfd3aa0e04934215a49bf9898df0", "name_or_path": "distilgpt2"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|