AlekseyKorshuk commited on
Commit
dfe1510
1 Parent(s): 41c91ef

huggingartists

Browse files
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ datasets:
4
+ - huggingartists/as-i-lay-dying
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/1584118378f9cfa83c281027ef8b2141.528x528x1.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">As I Lay Dying</div>
22
+ <a href="https://genius.com/artists/as-i-lay-dying">
23
+ <div style="text-align: center; font-size: 14px;">@as-i-lay-dying</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 As I Lay Dying.
38
+
39
+ Dataset is available [here](https://huggingface.co/datasets/huggingartists/as-i-lay-dying).
40
+ And can be used with:
41
+
42
+ ```python
43
+ from datasets import load_dataset
44
+
45
+ dataset = load_dataset("huggingartists/as-i-lay-dying")
46
+ ```
47
+
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2zq9ub8b/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 As I Lay Dying's lyrics.
53
+
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/cjg5ac7f) for full transparency and reproducibility.
55
+
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/cjg5ac7f/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/as-i-lay-dying')
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/as-i-lay-dying")
75
+
76
+ model = AutoModelWithLMHead.from_pretrained("huggingartists/as-i-lay-dying")
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 200,
33
+ "min_length": 100,
34
+ "temperature": 1.0,
35
+ "top_p": 0.95
36
+ }
37
+ },
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.12.3",
40
+ "use_cache": true,
41
+ "vocab_size": 50257
42
+ }
evaluation.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 2.888463020324707, "eval_runtime": 0.1778, "eval_samples_per_second": 67.482, "eval_steps_per_second": 11.247, "epoch": 50.0}
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0767b7d26a02bb334c9009ba9882002949dbb61223c28e9fa3f8249183a02272
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 sha256:1a9ac2c4913aa123a9be4a9be596faf8ee6c905bdbac8531e5767c07ba28da25
3
+ size 995603825
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace7793c62218ae81132ab5feb0c157c8e15a3f3ea180316a6c6446c4b104fb4
3
+ size 510403817
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb4eeb0d0fb1cbae287b7f0712f3eb3dd8f2ef51e8ef108a29fb7edf2c75af6
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d976a66ed4f5fc68a6027697098ed0ed8ec45e061f96a7ab9ad61ca80ebf3c
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 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.888463020324707,
3
+ "best_model_checkpoint": "output/as-i-lay-dying/checkpoint-24",
4
+ "epoch": 3.0,
5
+ "global_step": 24,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.62,
12
+ "learning_rate": 4.2347916539754844e-05,
13
+ "loss": 3.2892,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 2.9820306301116943,
19
+ "eval_runtime": 0.1663,
20
+ "eval_samples_per_second": 72.177,
21
+ "eval_steps_per_second": 12.029,
22
+ "step": 8
23
+ },
24
+ {
25
+ "epoch": 1.25,
26
+ "learning_rate": 2.009247481060283e-05,
27
+ "loss": 3.0726,
28
+ "step": 10
29
+ },
30
+ {
31
+ "epoch": 1.88,
32
+ "learning_rate": 0.00013197813593027427,
33
+ "loss": 3.0374,
34
+ "step": 15
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_loss": 2.95857834815979,
39
+ "eval_runtime": 0.1659,
40
+ "eval_samples_per_second": 72.316,
41
+ "eval_steps_per_second": 12.053,
42
+ "step": 16
43
+ },
44
+ {
45
+ "epoch": 2.5,
46
+ "learning_rate": 6.860000000000001e-05,
47
+ "loss": 2.8422,
48
+ "step": 20
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_loss": 2.888463020324707,
53
+ "eval_runtime": 0.1662,
54
+ "eval_samples_per_second": 72.182,
55
+ "eval_steps_per_second": 12.03,
56
+ "step": 24
57
+ }
58
+ ],
59
+ "max_steps": 400,
60
+ "num_train_epochs": 50,
61
+ "total_flos": 25084035072000.0,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e3fd09882ea2d12ca000a927e66f890279ec3e6a992c9f7b184a2952aeb3d4d
3
+ size 2863
vocab.json ADDED
The diff for this file is too large to render. See raw diff