bigjoedata
commited on
Commit
β’
b854631
1
Parent(s):
43ed3b5
Updated model after additional cleaning
Browse files- README.md +1 -0
- config.json +15 -3
- pytorch_model.bin +2 -2
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
README.md
CHANGED
@@ -1,3 +1,4 @@
|
|
|
|
1 |
# πΈ π₯ Rockbot π€ π§
|
2 |
A [GPT-2](https://huggingface.co/blog/how-to-generate) based lyrics generator fine-tuned on the writing styles of 16000 songs by 270 artists across MANY genres (not just rock).
|
3 |
|
|
|
1 |
+
|
2 |
# πΈ π₯ Rockbot π€ π§
|
3 |
A [GPT-2](https://huggingface.co/blog/how-to-generate) based lyrics generator fine-tuned on the writing styles of 16000 songs by 270 artists across MANY genres (not just rock).
|
4 |
|
config.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -9,22 +10,33 @@
|
|
9 |
"embd_pdrop": 0.1,
|
10 |
"eos_token_id": 50256,
|
11 |
"gradient_checkpointing": false,
|
|
|
|
|
|
|
12 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
15 |
"n_ctx": 1024,
|
16 |
"n_embd": 768,
|
17 |
"n_head": 12,
|
18 |
"n_inner": null,
|
19 |
-
"n_layer":
|
20 |
"n_positions": 1024,
|
21 |
-
"n_vocab": 50257,
|
22 |
"resid_pdrop": 0.1,
|
23 |
"summary_activation": null,
|
24 |
"summary_first_dropout": 0.1,
|
25 |
"summary_proj_to_labels": true,
|
26 |
"summary_type": "cls_index",
|
27 |
"summary_use_proj": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 50257
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilgpt2",
|
3 |
+
"_num_labels": 1,
|
4 |
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
6 |
"GPT2LMHeadModel"
|
|
|
10 |
"embd_pdrop": 0.1,
|
11 |
"eos_token_id": 50256,
|
12 |
"gradient_checkpointing": false,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0"
|
15 |
+
},
|
16 |
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
"layer_norm_epsilon": 1e-05,
|
21 |
"model_type": "gpt2",
|
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,
|
29 |
"summary_activation": null,
|
30 |
"summary_first_dropout": 0.1,
|
31 |
"summary_proj_to_labels": true,
|
32 |
"summary_type": "cls_index",
|
33 |
"summary_use_proj": true,
|
34 |
+
"task_specific_params": {
|
35 |
+
"text-generation": {
|
36 |
+
"do_sample": true,
|
37 |
+
"max_length": 50
|
38 |
+
}
|
39 |
+
},
|
40 |
"use_cache": true,
|
41 |
"vocab_size": 50257
|
42 |
}
|
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:a4c0be7281effcb32c545ca675f32621949b5d5369903edfadde8abd43c392f2
|
3 |
+
size 333973522
|
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"bos_token": {"content": "<|
|
|
|
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": "<|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": "<|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": "<|endoftext|>"}
|