AlekseyKorshuk commited on
Commit
6cebc60
1 Parent(s): 3b06ba3

huggingartists

Browse files
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ datasets:
4
+ - huggingartists/bushido-zho
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/6e5b165de8561df37790229c26b25692.959x959x1.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">BUSHIDO ZHO</div>
22
+ <a href="https://genius.com/artists/bushido-zho">
23
+ <div style="text-align: center; font-size: 14px;">@bushido-zho</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 BUSHIDO ZHO.
38
+
39
+ Dataset is available [here](https://huggingface.co/datasets/huggingartists/bushido-zho).
40
+ And can be used with:
41
+
42
+ ```python
43
+ from datasets import load_dataset
44
+
45
+ dataset = load_dataset("huggingartists/bushido-zho")
46
+ ```
47
+
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/vtfjc0qi/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 BUSHIDO ZHO's lyrics.
53
+
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/iwclgqsj) for full transparency and reproducibility.
55
+
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/iwclgqsj/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/bushido-zho')
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/bushido-zho")
75
+
76
+ model = AutoModelWithLMHead.from_pretrained("huggingartists/bushido-zho")
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 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "resid_pdrop": 0.1,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 200,
31
+ "min_length": 100,
32
+ "temperature": 1.0,
33
+ "top_p": 0.95
34
+ }
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.11.3",
38
+ "use_cache": true,
39
+ "vocab_size": 50257
40
+ }
evaluation.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 2.0637547969818115, "eval_runtime": 2.122, "eval_samples_per_second": 21.678, "eval_steps_per_second": 2.828, "epoch": 1.0}
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c220f065e5899ecfb8c32d64f76e30591f16f981509368f9bab01920da70a53
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 sha256:4745cc3a7d93f5a00a64ec1ace3e71daf28be661ee1394ed3062e3823341228e
3
+ size 995603825
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e9088c5bb36977562e9123c0f4faf5ca0c0251e14a0baa97506861be686811
3
+ size 510403817
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8bca9e035f0cebb6715b2bc26f8b806bab6d7dcf18d75ffc40483fb39631a12
3
+ size 14567
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5db905a92a509dd266dbe4c9a9a37720466ab7d8691a66201eebec362074dd3
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 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.0637547969818115,
3
+ "best_model_checkpoint": "output/bushido-zho/checkpoint-43",
4
+ "epoch": 1.0,
5
+ "global_step": 43,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.12,
12
+ "learning_rate": 0.0001326735050590528,
13
+ "loss": 2.7617,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.23,
18
+ "learning_rate": 0.00011969137173622343,
19
+ "loss": 2.5999,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.35,
24
+ "learning_rate": 9.99668233786982e-05,
25
+ "loss": 2.334,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.47,
30
+ "learning_rate": 7.61028648947222e-05,
31
+ "loss": 2.3462,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.58,
36
+ "learning_rate": 5.1248769967930697e-05,
37
+ "loss": 2.2185,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.7,
42
+ "learning_rate": 2.8684478392724447e-05,
43
+ "loss": 2.2835,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.81,
48
+ "learning_rate": 1.1387749692754382e-05,
49
+ "loss": 2.2393,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.93,
54
+ "learning_rate": 1.6411947996634035e-06,
55
+ "loss": 2.2366,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 1.0,
60
+ "eval_loss": 2.0637547969818115,
61
+ "eval_runtime": 2.0587,
62
+ "eval_samples_per_second": 22.345,
63
+ "eval_steps_per_second": 2.915,
64
+ "step": 43
65
+ }
66
+ ],
67
+ "max_steps": 43,
68
+ "num_train_epochs": 1,
69
+ "total_flos": 44942229504000.0,
70
+ "trial_name": null,
71
+ "trial_params": null
72
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:204095ff06170ece8145176e0d6db04075aaff427fa1822c967ec243b1d74dfb
3
+ size 2863
vocab.json ADDED
The diff for this file is too large to render. See raw diff