初始化项目，由ModelHub XC社区提供模型

Model: TristanBehrens/js-fakes-4bars Source: Original Platform
2026-08-08 00:05:18 +08:00
commit 27f2fc6f5b
8 changed files with 363 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,39 @@
+---
+
+tags:
+- gpt2
+- text-generation
+- music-modeling
+- music-generation
+
+widget:
+ - text: "PIECE_START"
+ - text: "PIECE_START STYLE=JSFAKES GENRE=JSFAKES TRACK_START INST=48 BAR_START NOTE_ON=60"
+ - text: "PIECE_START STYLE=JSFAKES GENRE=JSFAKES TRACK_START INST=48 BAR_START NOTE_ON=58"
+
+---
+
+
+# GPT-2 for Music
+
+Language Models such as GPT-2 can be used for Music Generation. The idea is to represent pieces of music as texts, effectively reducing the task to Language Generation.
+
+This model is a rather small instance of GPT-2 trained on [TristanBehrens/js-fakes-4bars](https://huggingface.co/datasets/TristanBehrens/js-fakes-4bars). The model generates 4 bars at a time of Bach-like chorales with four voices (soprano, alto, tenor, bass).
+
+If you are contribute, if you want to say hello, if you want to know more, find me on [LinkedIn](https://www.linkedin.com/in/dr-tristan-behrens-734967a2/)
+
+## Model description
+
+The model is GPT-2 with 6 decoders and 8 attention-heads each. The context length is 512. The embedding dimensions are 512 as well. The vocabulary size is 119.
+
+## Intended uses & limitations
+
+This model is just a proof of concept. It shows that HuggingFace can be used to compose music.
+
+### How to use
+
+There is a notebook in the repo that you can run on Google Colab.
+
+### Limitations and bias
+
+Since this model has been trained on a very small corpus of music, it is overfitting heavily. 
--- a/colab_jsfakes_generation.ipynb
+++ b/colab_jsfakes_generation.ipynb
@@ -0,0 +1,258 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "DWLOSBkp0A2U"
+   },
+   "source": [
+    "# GPT-2 for music.\n",
+    "\n",
+    "This notebook shows you how to generate music with GPT-2\n",
+    "\n",
+    "---\n",
+    "\n",
+    "## Install depencencies."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "6J_AnhV8D5p6"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install transformers\n",
+    "!pip install note_seq"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "RzhHhFll0JVl"
+   },
+   "source": [
+    "## Load the tokenizer and the model from 🤗 Hub."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "g3ih12FMD7bs"
+   },
+   "outputs": [],
+   "source": [
+    "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
+    "\n",
+    "tokenizer = AutoTokenizer.from_pretrained(\"TristanBehrens/js-fakes-4bars\")\n",
+    "model = AutoModelForCausalLM.from_pretrained(\"TristanBehrens/js-fakes-4bars\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "GxRBk--Q0P1q"
+   },
+   "source": [
+    "## How to generate."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "ZZSLX96ID7t8"
+   },
+   "outputs": [],
+   "source": [
+    "# Encode the conditioning tokens.\n",
+    "input_ids = tokenizer.encode(\"PIECE_START STYLE=JSFAKES GENRE=JSFAKES TRACK_START INST=48 BAR_START NOTE_ON=60\", return_tensors=\"pt\")\n",
+    "print(input_ids)\n",
+    "\n",
+    "# Generate more tokens.\n",
+    "generated_ids = model.generate(input_ids, max_length=500)\n",
+    "generated_sequence = tokenizer.decode(generated_ids[0])\n",
+    "print(generated_sequence)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "YfHXFugA0WdI"
+   },
+   "source": [
+    "## Convert the generated tokens to music that you can listen to."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "L3QMj8NyEBqs"
+   },
+   "outputs": [],
+   "source": [
+    "import note_seq\n",
+    "\n",
+    "NOTE_LENGTH_16TH_120BPM = 0.25 * 60 / 120\n",
+    "BAR_LENGTH_120BPM = 4.0 * 60 / 120\n",
+    "\n",
+    "def token_sequence_to_note_sequence(token_sequence, use_program=True, use_drums=True, instrument_mapper=None, only_piano=False):\n",
+    "\n",
+    "    if isinstance(token_sequence, str):\n",
+    "        token_sequence = token_sequence.split()\n",
+    "\n",
+    "    note_sequence = empty_note_sequence()\n",
+    "\n",
+    "    # Render all notes.\n",
+    "    current_program = 1\n",
+    "    current_is_drum = False\n",
+    "    current_instrument = 0\n",
+    "    track_count = 0\n",
+    "    for token_index, token in enumerate(token_sequence):\n",
+    "\n",
+    "        if token == \"PIECE_START\":\n",
+    "            pass\n",
+    "        elif token == \"PIECE_END\":\n",
+    "            print(\"The end.\")\n",
+    "            break\n",
+    "        elif token == \"TRACK_START\":\n",
+    "            current_bar_index = 0\n",
+    "            track_count += 1\n",
+    "            pass\n",
+    "        elif token == \"TRACK_END\":\n",
+    "            pass\n",
+    "        elif token == \"KEYS_START\":\n",
+    "            pass\n",
+    "        elif token == \"KEYS_END\":\n",
+    "            pass\n",
+    "        elif token.startswith(\"KEY=\"):\n",
+    "            pass\n",
+    "        elif token.startswith(\"INST\"):\n",
+    "            instrument = token.split(\"=\")[-1]\n",
+    "            if instrument != \"DRUMS\" and use_program:\n",
+    "                if instrument_mapper is not None:\n",
+    "                    if instrument in instrument_mapper:\n",
+    "                        instrument = instrument_mapper[instrument]\n",
+    "                current_program = int(instrument)\n",
+    "                current_instrument = track_count\n",
+    "                current_is_drum = False\n",
+    "            if instrument == \"DRUMS\" and use_drums:\n",
+    "                current_instrument = 0\n",
+    "                current_program = 0\n",
+    "                current_is_drum = True\n",
+    "        elif token == \"BAR_START\":\n",
+    "            current_time = current_bar_index * BAR_LENGTH_120BPM\n",
+    "            current_notes = {}\n",
+    "        elif token == \"BAR_END\":\n",
+    "            current_bar_index += 1\n",
+    "            pass\n",
+    "        elif token.startswith(\"NOTE_ON\"):\n",
+    "            pitch = int(token.split(\"=\")[-1])\n",
+    "            note = note_sequence.notes.add()\n",
+    "            note.start_time = current_time\n",
+    "            note.end_time = current_time + 4 * NOTE_LENGTH_16TH_120BPM\n",
+    "            note.pitch = pitch\n",
+    "            note.instrument = current_instrument\n",
+    "            note.program = current_program\n",
+    "            note.velocity = 80\n",
+    "            note.is_drum = current_is_drum\n",
+    "            current_notes[pitch] = note\n",
+    "        elif token.startswith(\"NOTE_OFF\"):\n",
+    "            pitch = int(token.split(\"=\")[-1])\n",
+    "            if pitch in current_notes:\n",
+    "                note = current_notes[pitch]\n",
+    "                note.end_time = current_time\n",
+    "        elif token.startswith(\"TIME_DELTA\"):\n",
+    "            delta = float(token.split(\"=\")[-1]) * NOTE_LENGTH_16TH_120BPM\n",
+    "            current_time += delta\n",
+    "        elif token.startswith(\"DENSITY=\"):\n",
+    "            pass\n",
+    "        elif token == \"[PAD]\":\n",
+    "            pass\n",
+    "        else:\n",
+    "            #print(f\"Ignored token {token}.\")\n",
+    "            pass\n",
+    "\n",
+    "    # Make the instruments right.\n",
+    "    instruments_drums = []\n",
+    "    for note in note_sequence.notes:\n",
+    "        pair = [note.program, note.is_drum]\n",
+    "        if pair not in instruments_drums:\n",
+    "            instruments_drums += [pair]\n",
+    "        note.instrument = instruments_drums.index(pair)\n",
+    "\n",
+    "    if only_piano:\n",
+    "        for note in note_sequence.notes:\n",
+    "            if not note.is_drum:\n",
+    "                note.instrument = 0\n",
+    "                note.program = 0\n",
+    "\n",
+    "    return note_sequence\n",
+    "\n",
+    "def empty_note_sequence(qpm=120.0, total_time=0.0):\n",
+    "    note_sequence = note_seq.protobuf.music_pb2.NoteSequence()\n",
+    "    note_sequence.tempos.add().qpm = qpm\n",
+    "    note_sequence.ticks_per_quarter = note_seq.constants.STANDARD_PPQ\n",
+    "    note_sequence.total_time = total_time\n",
+    "    return note_sequence"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "ZYpukydNESDF"
+   },
+   "outputs": [],
+   "source": [
+    "input_ids = tokenizer.encode(\"PIECE_START STYLE=JSFAKES GENRE=JSFAKES TRACK_START INST=48 BAR_START NOTE_ON=61\", return_tensors=\"pt\")\n",
+    "generated_ids = model.generate(input_ids, max_length=500, temperature=1.0)\n",
+    "generated_sequence = tokenizer.decode(generated_ids[0])\n",
+    "\n",
+    "note_sequence = token_sequence_to_note_sequence(generated_sequence)\n",
+    "\n",
+    "synth = note_seq.midi_synth.synthesize\n",
+    "note_seq.plot_sequence(note_sequence)\n",
+    "note_seq.play_sequence(note_sequence, synth)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "d1x6HeF90kkO"
+   },
+   "source": [
+    "# Thank you!"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "collapsed_sections": [],
+   "name": "colab_jsfakes_generation.ipynb",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 512,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 512,
+  "pad_token_id": 3,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "use_cache": true,
+  "vocab_size": 119
+}
--- a/pytorch_model.bin
+++ b/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ee67cbca1e3005006503fbd2068873b8b1a064ece8880edcc7300a3e221ae1
+size 78557661
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1 @@
+{"pad_token": "[PAD]"}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1 @@
+{"version":"1.0","truncation":{"max_length":512,"strategy":"LongestFirst","stride":0},"padding":null,"added_tokens":[{"id":0,"special":true,"content":"[UNK]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":1,"special":true,"content":"[CLS]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":2,"special":true,"content":"[SEP]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":3,"special":true,"content":"[PAD]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":4,"special":true,"content":"[MASK]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false}],"normalizer":null,"pre_tokenizer":{"type":"WhitespaceSplit"},"post_processor":null,"decoder":null,"model":{"type":"WordLevel","vocab":{"[UNK]":0,"[CLS]":1,"[SEP]":2,"[PAD]":3,"[MASK]":4,"TIME_DELTA=4":5,"TIME_DELTA=2":6,"BAR_END":7,"BAR_START":8,"TRACK_START":9,"TRACK_END":10,"NOTE_OFF=67":11,"NOTE_ON=67":12,"NOTE_ON=65":13,"NOTE_OFF=65":14,"NOTE_ON=62":15,"NOTE_OFF=62":16,"NOTE_ON=60":17,"NOTE_OFF=60":18,"TIME_DELTA=8":19,"NOTE_OFF=64":20,"NOTE_ON=64":21,"NOTE_ON=63":22,"NOTE_OFF=63":23,"NOTE_OFF=66":24,"NOTE_ON=66":25,"NOTE_OFF=69":26,"NOTE_ON=69":27,"NOTE_OFF=68":28,"NOTE_ON=68":29,"NOTE_ON=61":30,"NOTE_OFF=61":31,"NOTE_OFF=58":32,"NOTE_ON=58":33,"NOTE_ON=55":34,"NOTE_OFF=55":35,"NOTE_OFF=70":36,"NOTE_ON=70":37,"NOTE_OFF=59":38,"NOTE_ON=59":39,"NOTE_OFF=57":40,"NOTE_ON=57":41,"NOTE_ON=56":42,"NOTE_OFF=56":43,"NOTE_OFF=53":44,"NOTE_ON=53":45,"NOTE_OFF=71":46,"NOTE_ON=71":47,"NOTE_ON=72":48,"NOTE_OFF=72":49,"NOTE_ON=54":50,"NOTE_OFF=54":51,"NOTE_ON=52":52,"NOTE_OFF=52":53,"NOTE_OFF=50":54,"NOTE_ON=50":55,"NOTE_ON=51":56,"NOTE_OFF=51":57,"NOTE_ON=48":58,"NOTE_OFF=48":59,"NOTE_OFF=73":60,"NOTE_ON=73":61,"NOTE_OFF=74":62,"NOTE_ON=74":63,"NOTE_OFF=49":64,"NOTE_ON=49":65,"NOTE_ON=47":66,"NOTE_OFF=47":67,"NOTE_ON=75":68,"NOTE_OFF=75":69,"NOTE_OFF=46":70,"NOTE_ON=46":71,"INST=24":72,"PIECE_END":73,"INST=48":74,"GENRE=JSFAKES":75,"INST=0":76,"PIECE_START":77,"STYLE=JSFAKES":78,"INST=32":79,"TIME_DELTA=1":80,"NOTE_OFF=45":81,"NOTE_ON=45":82,"NOTE_ON=76":83,"NOTE_OFF=76":84,"TIME_DELTA=6":85,"NOTE_OFF=44":86,"NOTE_ON=44":87,"TIME_DELTA=12":88,"NOTE_ON=43":89,"NOTE_OFF=43":90,"NOTE_OFF=77":91,"NOTE_ON=77":92,"NOTE_OFF=78":93,"NOTE_ON=78":94,"NOTE_OFF=41":95,"NOTE_ON=41":96,"NOTE_ON=42":97,"NOTE_OFF=42":98,"NOTE_ON=79":99,"NOTE_OFF=79":100,"NOTE_OFF=40":101,"NOTE_ON=40":102,"TIME_DELTA=16":103,"NOTE_ON=39":104,"NOTE_OFF=39":105,"NOTE_OFF=80":106,"NOTE_ON=80":107,"TIME_DELTA=3":108,"NOTE_OFF=38":109,"NOTE_ON=38":110,"NOTE_OFF=37":111,"NOTE_ON=37":112,"NOTE_ON=36":113,"NOTE_OFF=36":114,"NOTE_OFF=81":115,"NOTE_ON=81":116,"TIME_DELTA=7":117,"TIME_DELTA=10":118},"unk_token":"[UNK]"}}
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1 @@
+{"tokenizer_class": "PreTrainedTokenizerFast"}
				`@@ -0,0 +1 @@`
				{"version":"1.0","truncation":{"max_length":512,"strategy":"LongestFirst","stride":0},"padding":null,"added_tokens":[{"id":0,"special":true,"content":"[UNK]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":1,"special":true,"content":"[CLS]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":2,"special":true,"content":"[SEP]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":3,"special":true,"content":"[PAD]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":4,"special":true,"content":"[MASK]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false}],"normalizer":null,"pre_tokenizer":{"type":"WhitespaceSplit"},"post_processor":null,"decoder":null,"model":{"type":"WordLevel","vocab":{"[UNK]":0,"[CLS]":1,"[SEP]":2,"[PAD]":3,"[MASK]":4,"TIME_DELTA=4":5,"TIME_DELTA=2":6,"BAR_END":7,"BAR_START":8,"TRACK_START":9,"TRACK_END":10,"NOTE_OFF=67":11,"NOTE_ON=67":12,"NOTE_ON=65":13,"NOTE_OFF=65":14,"NOTE_ON=62":15,"NOTE_OFF=62":16,"NOTE_ON=60":17,"NOTE_OFF=60":18,"TIME_DELTA=8":19,"NOTE_OFF=64":20,"NOTE_ON=64":21,"NOTE_ON=63":22,"NOTE_OFF=63":23,"NOTE_OFF=66":24,"NOTE_ON=66":25,"NOTE_OFF=69":26,"NOTE_ON=69":27,"NOTE_OFF=68":28,"NOTE_ON=68":29,"NOTE_ON=61":30,"NOTE_OFF=61":31,"NOTE_OFF=58":32,"NOTE_ON=58":33,"NOTE_ON=55":34,"NOTE_OFF=55":35,"NOTE_OFF=70":36,"NOTE_ON=70":37,"NOTE_OFF=59":38,"NOTE_ON=59":39,"NOTE_OFF=57":40,"NOTE_ON=57":41,"NOTE_ON=56":42,"NOTE_OFF=56":43,"NOTE_OFF=53":44,"NOTE_ON=53":45,"NOTE_OFF=71":46,"NOTE_ON=71":47,"NOTE_ON=72":48,"NOTE_OFF=72":49,"NOTE_ON=54":50,"NOTE_OFF=54":51,"NOTE_ON=52":52,"NOTE_OFF=52":53,"NOTE_OFF=50":54,"NOTE_ON=50":55,"NOTE_ON=51":56,"NOTE_OFF=51":57,"NOTE_ON=48":58,"NOTE_OFF=48":59,"NOTE_OFF=73":60,"NOTE_ON=73":61,"NOTE_OFF=74":62,"NOTE_ON=74":63,"NOTE_OFF=49":64,"NOTE_ON=49":65,"NOTE_ON=47":66,"NOTE_OFF=47":67,"NOTE_ON=75":68,"NOTE_OFF=75":69,"NOTE_OFF=46":70,"NOTE_ON=46":71,"INST=24":72,"PIECE_END":73,"INST=48":74,"GENRE=JSFAKES":75,"INST=0":76,"PIECE_START":77,"STYLE=JSFAKES":78,"INST=32":79,"TIME_DELTA=1":80,"NOTE_OFF=45":81,"NOTE_ON=45":82,"NOTE_ON=76":83,"NOTE_OFF=76":84,"TIME_DELTA=6":85,"NOTE_OFF=44":86,"NOTE_ON=44":87,"TIME_DELTA=12":88,"NOTE_ON=43":89,"NOTE_OFF=43":90,"NOTE_OFF=77":91,"NOTE_ON=77":92,"NOTE_OFF=78":93,"NOTE_ON=78":94,"NOTE_OFF=41":95,"NOTE_ON=41":96,"NOTE_ON=42":97,"NOTE_OFF=42":98,"NOTE_ON=79":99,"NOTE_OFF=79":100,"NOTE_OFF=40":101,"NOTE_ON=40":102,"TIME_DELTA=16":103,"NOTE_ON=39":104,"NOTE_OFF=39":105,"NOTE_OFF=80":106,"NOTE_ON=80":107,"TIME_DELTA=3":108,"NOTE_OFF=38":109,"NOTE_ON=38":110,"NOTE_OFF=37":111,"NOTE_ON=37":112,"NOTE_ON=36":113,"NOTE_OFF=36":114,"NOTE_OFF=81":115,"NOTE_ON=81":116,"TIME_DELTA=7":117,"TIME_DELTA=10":118},"unk_token":"[UNK]"}}
				`@@ -0,0 +1 @@`
				`{"tokenizer_class": "PreTrainedTokenizerFast"}`