zhangysk paralym commited on
Commit
c416a50
1 Parent(s): dcc0301

Update README.md (#3)

Browse files

- Update README.md (161b3eeded769123c06fb4f1b8f34fb9724a492a)


Co-authored-by: paralym <paralym@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +13 -2
README.md CHANGED
@@ -7,6 +7,12 @@ tags:
7
  - music
8
  - art
9
  ---
 
 
 
 
 
 
10
  ## SMuPT: Symbolic Music Generative Pre-trained Transformer
11
 
12
  SMuPT is a series of pre-trained models for symbolic music generation. It was trained on a large-scale dataset of symbolic music, including millions of monophonic and polyphonic pieces from different genres and styles. The models are trained with the LLama2 architecture, and can be further used for downstream music generation tasks such as melody generation, accompaniment generation, and multi-track music generation.
@@ -123,9 +129,14 @@ Use CURL to query the server directly, note that the newline token `\n` is repre
123
  ```shell
124
  curl 'http://localhost:6000/api' -X 'PUT' -H 'Content-Type: application/json; charset=UTF-8' -d '{"prompts":["X:1<n>L:1/8<n>Q:1/8=200<n>M:4/4<n>K:Gmin<n>|:\"Gm\" BGdB"], "tokens_to_generate":4096}'
125
  ```
126
- Output:
127
  ```shell
128
- X:1<n>L:1/8<n>Q:1/8=200<n>M:4/4<n>K:Gmin<n>|:\"Gm\" BGdB fdBG |\"F\" AFcF dFcF |\"Gm\" BGdG gFBF |\"F\" AFAG AF F2 |\"Gm\" BGBd fffd |\"F\" cdcB cdeg | <n>\"Gm\" fdcB\"Eb\" AFcA |1 BGFG\"F\" AFGc :|2 BGFG\"F\" AF F2 ||<eos>
 
 
 
 
 
129
  ```
130
 
131
  Once you encode the generated tokens into audio, you will hear the following music.
 
7
  - music
8
  - art
9
  ---
10
+
11
+ <div align="center">
12
+ <img src="Yi_logo.svg" width="150px" style="display: inline-block;">
13
+ <img src="m-a-p.png" width="150px" style="display: inline-block;">
14
+ </div>
15
+
16
  ## SMuPT: Symbolic Music Generative Pre-trained Transformer
17
 
18
  SMuPT is a series of pre-trained models for symbolic music generation. It was trained on a large-scale dataset of symbolic music, including millions of monophonic and polyphonic pieces from different genres and styles. The models are trained with the LLama2 architecture, and can be further used for downstream music generation tasks such as melody generation, accompaniment generation, and multi-track music generation.
 
129
  ```shell
130
  curl 'http://localhost:6000/api' -X 'PUT' -H 'Content-Type: application/json; charset=UTF-8' -d '{"prompts":["X:1<n>L:1/8<n>Q:1/8=200<n>M:4/4<n>K:Gmin<n>|:\"Gm\" BGdB"], "tokens_to_generate":4096}'
131
  ```
132
+ Processed Output:
133
  ```shell
134
+ X:1
135
+ L:1/8
136
+ Q:1/8=200
137
+ M:4/4<n>K:Gmin
138
+ |:\"Gm\" BGdB fdBG |\"F\" AFcF dFcF |\"Gm\" BGdG gFBF |\"F\" AFAG AF F2 |\"Gm\" BGBd fffd |\"F\" cdcB cdeg |
139
+ \"Gm\" fdcB\"Eb\" AFcA |1 BGFG\"F\" AFGc :|2 BGFG\"F\" AF F2 ||<eos>
140
  ```
141
 
142
  Once you encode the generated tokens into audio, you will hear the following music.