bigjoedata
commited on
Commit
•
20ef84e
1
Parent(s):
6721bba
Added new artists, longer training
Browse files- config.json +13 -15
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
- vocab.json +0 -0
config.json
CHANGED
@@ -1,31 +1,29 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "aitextgen/pytorch_model_124M.bin",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
6 |
],
|
7 |
-
"attn_pdrop": 0.
|
8 |
-
"bos_token_id":
|
9 |
-
"embd_pdrop": 0.
|
10 |
-
"eos_token_id":
|
11 |
"gradient_checkpointing": false,
|
12 |
"initializer_range": 0.02,
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
15 |
-
"n_ctx":
|
16 |
-
"n_embd":
|
17 |
-
"n_head":
|
18 |
"n_inner": null,
|
19 |
-
"n_layer":
|
20 |
-
"n_positions":
|
21 |
-
"
|
22 |
-
"resid_pdrop": 0.1,
|
23 |
"summary_activation": null,
|
24 |
-
"summary_first_dropout": 0.
|
25 |
"summary_proj_to_labels": true,
|
26 |
"summary_type": "cls_index",
|
27 |
"summary_use_proj": true,
|
28 |
-
"transformers_version": "4.
|
29 |
"use_cache": true,
|
30 |
-
"vocab_size":
|
31 |
}
|
1 |
{
|
|
|
2 |
"activation_function": "gelu_new",
|
3 |
"architectures": [
|
4 |
"GPT2LMHeadModel"
|
5 |
],
|
6 |
+
"attn_pdrop": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"embd_pdrop": 0.0,
|
9 |
+
"eos_token_id": 0,
|
10 |
"gradient_checkpointing": false,
|
11 |
"initializer_range": 0.02,
|
12 |
"layer_norm_epsilon": 1e-05,
|
13 |
"model_type": "gpt2",
|
14 |
+
"n_ctx": 512,
|
15 |
+
"n_embd": 256,
|
16 |
+
"n_head": 8,
|
17 |
"n_inner": null,
|
18 |
+
"n_layer": 8,
|
19 |
+
"n_positions": 512,
|
20 |
+
"resid_pdrop": 0.0,
|
|
|
21 |
"summary_activation": null,
|
22 |
+
"summary_first_dropout": 0.0,
|
23 |
"summary_proj_to_labels": true,
|
24 |
"summary_type": "cls_index",
|
25 |
"summary_use_proj": true,
|
26 |
+
"transformers_version": "4.3.2",
|
27 |
"use_cache": true,
|
28 |
+
"vocab_size": 75000
|
29 |
}
|
merges.txt
CHANGED
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 sha256:588e5186b28450aa011770f686a8d86652a7e429e15460e56b7f03cc14690ede
|
3 |
+
size 104737544
|
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"bos_token": {"content": "<|
|
1 |
+
{"bos_token": {"content": "<|endoftext|>", "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": "<|endoftext|>"}
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|
|
1 |
+
{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "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": "<|endoftext|>"}
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|