AlekseyKorshuk commited on
Commit
96448fa
1 Parent(s): 32e38b4

huggingartists

Browse files
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ datasets:
4
+ - huggingartists/gunna
5
+ tags:
6
+ - huggingartists
7
+ - lyrics
8
+ - lm-head
9
+ - causal-lm
10
+ widget:
11
+ - text: "I am"
12
+ ---
13
+
14
+ <div class="inline-flex flex-col" style="line-height: 1.5;">
15
+ <div class="flex">
16
+ <div
17
+ style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/18e3833ac527a4bf14ddf2acef834795.640x640x1.jpg&#39;)">
18
+ </div>
19
+ </div>
20
+ <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
21
+ <div style="text-align: center; font-size: 16px; font-weight: 800">Gunna</div>
22
+ <a href="https://genius.com/artists/gunna">
23
+ <div style="text-align: center; font-size: 14px;">@gunna</div>
24
+ </a>
25
+ </div>
26
+
27
+ I was made with [huggingartists](https://github.com/AlekseyKorshuk/huggingartists).
28
+
29
+ Create your own bot based on your favorite artist with [the demo](https://colab.research.google.com/github/AlekseyKorshuk/huggingartists/blob/master/huggingartists-demo.ipynb)!
30
+
31
+ ## How does it work?
32
+
33
+ To understand how the model was developed, check the [W&B report](https://wandb.ai/huggingartists/huggingartists/reportlist).
34
+
35
+ ## Training data
36
+
37
+ The model was trained on lyrics from Gunna.
38
+
39
+ Dataset is available [here](https://huggingface.co/datasets/huggingartists/gunna).
40
+ And can be used with:
41
+
42
+ ```python
43
+ from datasets import load_dataset
44
+
45
+ dataset = load_dataset("huggingartists/gunna")
46
+ ```
47
+
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/vcyblers/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
49
+
50
+ ## Training procedure
51
+
52
+ The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Gunna's lyrics.
53
+
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3c1xymw6) for full transparency and reproducibility.
55
+
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3c1xymw6/artifacts) is logged and versioned.
57
+
58
+ ## How to use
59
+
60
+ You can use this model directly with a pipeline for text generation:
61
+
62
+ ```python
63
+ from transformers import pipeline
64
+ generator = pipeline('text-generation',
65
+ model='huggingartists/gunna')
66
+ generator("I am", num_return_sequences=5)
67
+ ```
68
+
69
+ Or with Transformers library:
70
+
71
+ ```python
72
+ from transformers import AutoTokenizer, AutoModelWithLMHead
73
+
74
+ tokenizer = AutoTokenizer.from_pretrained("huggingartists/gunna")
75
+
76
+ model = AutoModelWithLMHead.from_pretrained("huggingartists/gunna")
77
+ ```
78
+
79
+ ## Limitations and bias
80
+
81
+ The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
82
+
83
+ In addition, the data present in the user's tweets further affects the text generated by the model.
84
+
85
+ ## About
86
+
87
+ *Built by Aleksey Korshuk*
88
+
89
+ [![Follow](https://img.shields.io/github/followers/AlekseyKorshuk?style=social)](https://github.com/AlekseyKorshuk)
90
+
91
+ [![Follow](https://img.shields.io/twitter/follow/alekseykorshuk?style=social)](https://twitter.com/intent/follow?screen_name=alekseykorshuk)
92
+
93
+ [![Follow](https://img.shields.io/badge/dynamic/json?color=blue&label=Telegram%20Channel&query=%24.result&url=https%3A%2F%2Fapi.telegram.org%2Fbot1929545866%3AAAFGhV-KKnegEcLiyYJxsc4zV6C-bdPEBtQ%2FgetChatMemberCount%3Fchat_id%3D-1001253621662&style=social&logo=telegram)](https://t.me/joinchat/_CQ04KjcJ-4yZTky)
94
+
95
+ For more details, visit the project repository.
96
+
97
+ [![GitHub stars](https://img.shields.io/github/stars/AlekseyKorshuk/huggingartists?style=social)](https://github.com/AlekseyKorshuk/huggingartists)
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
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": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_weights": true,
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
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 200,
32
+ "min_length": 100,
33
+ "temperature": 1.0,
34
+ "top_p": 0.95
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.10.2",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
evaluation.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 3.6241421699523926, "eval_runtime": 9.333, "eval_samples_per_second": 22.715, "eval_steps_per_second": 2.893, "epoch": 1.0}
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:288fea5b61330fc7d0a8757880fb8eb4a7e1af44ca574e8a0463b155db51d1f6
3
+ size 497764120
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052cb85ad0328fcf1436bc93a587e20735d2b111b2713073598cccd4528c325f
3
+ size 995603825
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5101919ee5ef164163df65d5713eab920af91d4404adba0e803229c1bd4186ac
3
+ size 510403817
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d881c42603f695d2ce6a14e9d3d35fd4bebbe6cb5f1c95af8cd42bf41574b396
3
+ size 14567
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1d88b13877a3ca6e9698ffdcfa6a7f43541317791f83d4979bba45ff1b17524
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.6241421699523926,
3
+ "best_model_checkpoint": "output/gunna/checkpoint-160",
4
+ "epoch": 1.0,
5
+ "global_step": 160,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.03,
12
+ "learning_rate": 0.0001368696722497127,
13
+ "loss": 4.356,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.06,
18
+ "learning_rate": 0.0001358818702356616,
19
+ "loss": 4.1179,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.09,
24
+ "learning_rate": 0.00013424610703122953,
25
+ "loss": 4.0264,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.12,
30
+ "learning_rate": 0.00013197813593027427,
31
+ "loss": 4.0528,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.16,
36
+ "learning_rate": 0.00012909979873429716,
37
+ "loss": 3.9366,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.19,
42
+ "learning_rate": 0.0001256388154039546,
43
+ "loss": 3.8881,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.22,
48
+ "learning_rate": 0.00012162851710068375,
49
+ "loss": 3.7806,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.25,
54
+ "learning_rate": 0.00011710752518939715,
55
+ "loss": 3.7294,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.28,
60
+ "learning_rate": 0.00011211937929362608,
61
+ "loss": 3.7043,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.31,
66
+ "learning_rate": 0.00010671211798514472,
67
+ "loss": 3.7065,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.34,
72
+ "learning_rate": 0.00010093781614626346,
73
+ "loss": 3.5885,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.38,
78
+ "learning_rate": 9.485208346024516e-05,
79
+ "loss": 3.5777,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.41,
84
+ "learning_rate": 8.851352885965611e-05,
85
+ "loss": 3.6253,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.44,
90
+ "learning_rate": 8.19831960903064e-05,
91
+ "loss": 3.6754,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.47,
96
+ "learning_rate": 7.532397582660788e-05,
97
+ "loss": 3.7343,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.5,
102
+ "learning_rate": 6.86e-05,
103
+ "loss": 3.6731,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.53,
108
+ "learning_rate": 6.187602417339214e-05,
109
+ "loss": 3.5158,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.56,
114
+ "learning_rate": 5.52168039096936e-05,
115
+ "loss": 3.4779,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 0.59,
120
+ "learning_rate": 4.8686471140343896e-05,
121
+ "loss": 3.7252,
122
+ "step": 95
123
+ },
124
+ {
125
+ "epoch": 0.62,
126
+ "learning_rate": 4.2347916539754844e-05,
127
+ "loss": 3.5483,
128
+ "step": 100
129
+ },
130
+ {
131
+ "epoch": 0.66,
132
+ "learning_rate": 3.6262183853736556e-05,
133
+ "loss": 3.6806,
134
+ "step": 105
135
+ },
136
+ {
137
+ "epoch": 0.69,
138
+ "learning_rate": 3.0487882014855305e-05,
139
+ "loss": 3.5955,
140
+ "step": 110
141
+ },
142
+ {
143
+ "epoch": 0.72,
144
+ "learning_rate": 2.5080620706373927e-05,
145
+ "loss": 3.5443,
146
+ "step": 115
147
+ },
148
+ {
149
+ "epoch": 0.75,
150
+ "learning_rate": 2.0092474810602843e-05,
151
+ "loss": 3.5015,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.78,
156
+ "learning_rate": 1.557148289931624e-05,
157
+ "loss": 3.4182,
158
+ "step": 125
159
+ },
160
+ {
161
+ "epoch": 0.81,
162
+ "learning_rate": 1.1561184596045389e-05,
163
+ "loss": 3.5311,
164
+ "step": 130
165
+ },
166
+ {
167
+ "epoch": 0.84,
168
+ "learning_rate": 8.100201265702852e-06,
169
+ "loss": 3.6302,
170
+ "step": 135
171
+ },
172
+ {
173
+ "epoch": 0.88,
174
+ "learning_rate": 5.22186406972573e-06,
175
+ "loss": 3.5087,
176
+ "step": 140
177
+ },
178
+ {
179
+ "epoch": 0.91,
180
+ "learning_rate": 2.953892968770475e-06,
181
+ "loss": 3.5036,
182
+ "step": 145
183
+ },
184
+ {
185
+ "epoch": 0.94,
186
+ "learning_rate": 1.3181297643383925e-06,
187
+ "loss": 3.4784,
188
+ "step": 150
189
+ },
190
+ {
191
+ "epoch": 0.97,
192
+ "learning_rate": 3.303277502872983e-07,
193
+ "loss": 3.2405,
194
+ "step": 155
195
+ },
196
+ {
197
+ "epoch": 1.0,
198
+ "learning_rate": 0.0,
199
+ "loss": 3.4995,
200
+ "step": 160
201
+ },
202
+ {
203
+ "epoch": 1.0,
204
+ "eval_loss": 3.6241421699523926,
205
+ "eval_runtime": 9.1367,
206
+ "eval_samples_per_second": 23.203,
207
+ "eval_steps_per_second": 2.955,
208
+ "step": 160
209
+ }
210
+ ],
211
+ "max_steps": 160,
212
+ "num_train_epochs": 1,
213
+ "total_flos": 166443024384000.0,
214
+ "trial_name": null,
215
+ "trial_params": null
216
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b9a565903d96345e80056adfb1076c9a92ccbdb40543022a79d3d10570bf5ce
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff