AlekseyKorshuk commited on
Commit
a976d9a
1 Parent(s): 61b8442

huggingartists

Browse files
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ datasets:
4
+ - huggingartists/max-korzh
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/a1486b5b6f28eeec202b55e983e464c5.567x567x1.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">Макс Корж (Max Korzh)</div>
22
+ <a href="https://genius.com/artists/max-korzh">
23
+ <div style="text-align: center; font-size: 14px;">@max-korzh</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 Макс Корж (Max Korzh).
38
+
39
+ Dataset is available [here](https://huggingface.co/datasets/huggingartists/max-korzh).
40
+ And can be used with:
41
+
42
+ ```python
43
+ from datasets import load_dataset
44
+
45
+ dataset = load_dataset("huggingartists/max-korzh")
46
+ ```
47
+
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2lupo5gy/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 Макс Корж (Max Korzh)'s lyrics.
53
+
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1pm64gaa) for full transparency and reproducibility.
55
+
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1pm64gaa/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/max-korzh')
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/max-korzh")
75
+
76
+ model = AutoModelWithLMHead.from_pretrained("huggingartists/max-korzh")
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": "4.10.0",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
evaluation.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 1.8468588590621948, "eval_runtime": 4.2851, "eval_samples_per_second": 21.936, "eval_steps_per_second": 2.8, "epoch": 1.0}
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e19ef419f6662fcd6d0e140e88c240407065e782a85e6f4ca91fe9a0ec4a8186
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 sha256:7857b507355d1c865c2ffff697fe4079cc00459d1e66c02e82627787272d3db4
3
+ size 995603825
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aba2150545cba0dc299c10fdafa0cb4ec9f35d6c057643ec00bbbefa7d19923e
3
+ size 510403817
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb2cfcd172db8d520442e469438e46a8c0f7deb23577bc1c5a2fbf8cc3dea470
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8250a5b2245967ba67d3befe35c6f8287cf95e55bfd78f4174de3304afdd1fa
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 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8468588590621948,
3
+ "best_model_checkpoint": "output/max-korzh/checkpoint-66",
4
+ "epoch": 1.0,
5
+ "global_step": 66,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 0.00013526627358699495,
13
+ "loss": 2.4173,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.15,
18
+ "learning_rate": 0.00012957411177772776,
19
+ "loss": 2.2555,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.23,
24
+ "learning_rate": 0.00012044442080070213,
25
+ "loss": 2.0536,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.3,
30
+ "learning_rate": 0.0001083919039965842,
31
+ "loss": 2.0403,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.38,
36
+ "learning_rate": 9.409604445829847e-05,
37
+ "loss": 1.9983,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.45,
42
+ "learning_rate": 7.836279790554737e-05,
43
+ "loss": 1.9702,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.53,
48
+ "learning_rate": 6.207915542933309e-05,
49
+ "loss": 1.9274,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.61,
54
+ "learning_rate": 4.616313771642488e-05,
55
+ "loss": 1.9929,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.68,
60
+ "learning_rate": 3.151203992254603e-05,
61
+ "loss": 1.927,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.76,
66
+ "learning_rate": 1.8951844985992186e-05,
67
+ "loss": 1.9614,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.83,
72
+ "learning_rate": 9.190657300387505e-06,
73
+ "loss": 1.8335,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.91,
78
+ "learning_rate": 2.778782010045488e-06,
79
+ "loss": 1.8942,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.98,
84
+ "learning_rate": 7.770053204565375e-08,
85
+ "loss": 1.8146,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 1.0,
90
+ "eval_loss": 1.8468588590621948,
91
+ "eval_runtime": 4.2001,
92
+ "eval_samples_per_second": 22.381,
93
+ "eval_steps_per_second": 2.857,
94
+ "step": 66
95
+ }
96
+ ],
97
+ "max_steps": 66,
98
+ "num_train_epochs": 1,
99
+ "total_flos": 68458512384000.0,
100
+ "trial_name": null,
101
+ "trial_params": null
102
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a5897b7c896836605065084f094d9fc3837ef2caf81e230c000530bc5ad382
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff