Add initial model files

.gitattributes

@@ -14,6 +14,7 @@
 *.npy filter=lfs diff=lfs merge=lfs -text
 *.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
+*.onnx.data 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

README.md

@@ -1,3 +1,36 @@
 ---
 license: apache-2.0
+base_model:
+- m-a-p/YuE-s2-1B-general
+tags:
+- yue
+- music
 ---
+
+# YuEの4bit量子化+onnx形式への変換モデルです。
+ベースモデル  
+[m-a-p/YuE-s2-1B-general](https://huggingface.co/m-a-p/YuE-s2-1B-general)  
+上記のモデルを4bit量子化とonnx形式へ変換したモデルです。  
+性能劣化がありますのでご注意ください。
+  
+githubにて、このモデルを使用したツールを作成中です。  
+[YuE-q4onnx-win](https://github.com/siouni/YuE-q4onnx-win)
+
+## 変換方法
+Generate models using Model Builder  
+[https://onnxruntime.ai/docs/genai/howto/build-model.html](https://onnxruntime.ai/docs/genai/howto/build-model.html)  
+適当なフォルダに仮想環境を作り、onnxruntime（optimum）とonnxruntime-genaiをインストールします。  
+私はwindows11+python 3.10で実行しました。  
+また、pwshを使用していますので、コマンドプロンプトの場合は適当に読み替えてください。
+```CLI
+python -m venv venv
+venv\Scripts\activate
+# linuxなら↓
+venv/Script/activate
+
+pip install optimum[onnxruntime]
+pip install --pre onnxruntime-genai
+
+python -m onnxruntime_genai.models.builder -m m-a-p/YuE-s2-1B-general -o ./onnx_models/YuE-s2-1B-general-onnx-q4 -p int4 -e cuda -c ./models/
+curl https://huggingface.co/m-a-p/YuE-s2-1B-general/resolve/main/config.json?download=true > ./onnx_models/YuE-s2-1B-general-onnx-q4/config.json
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "m-a-p/YuE-s2-1B-general",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 83840
+}

genai_config.json

@@ -0,0 +1,55 @@
+{
+    "model": {
+        "bos_token_id": 1,
+        "context_length": 8192,
+        "decoder": {
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": [
+                    {
+                        "cuda": {
+                            "enable_cuda_graph": "0"
+                        }
+                    }
+                ]
+            },
+            "filename": "model.onnx",
+            "head_size": 128,
+            "hidden_size": 2048,
+            "inputs": {
+                "input_ids": "input_ids",
+                "attention_mask": "attention_mask",
+                "past_key_names": "past_key_values.%d.key",
+                "past_value_names": "past_key_values.%d.value"
+            },
+            "outputs": {
+                "logits": "logits",
+                "present_key_names": "present.%d.key",
+                "present_value_names": "present.%d.value"
+            },
+            "num_attention_heads": 16,
+            "num_hidden_layers": 32,
+            "num_key_value_heads": 16
+        },
+        "eos_token_id": 2,
+        "pad_token_id": 2,
+        "type": "llama",
+        "vocab_size": 83840
+    },
+    "search": {
+        "diversity_penalty": 0.0,
+        "do_sample": false,
+        "early_stopping": true,
+        "length_penalty": 1.0,
+        "max_length": 8192,
+        "min_length": 0,
+        "no_repeat_ngram_size": 0,
+        "num_beams": 1,
+        "num_return_sequences": 1,
+        "past_present_share_buffer": true,
+        "repetition_penalty": 1.0,
+        "temperature": 1.0,
+        "top_k": 1,
+        "top_p": 1.0
+    }
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ca42670f16e4ae8f3776664b71fb086af4bc0eb418d405f5754fd7ea9258ec
+size 211828

model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f767b1bd61d80567873e6afcd8b7c33465e8979689511cc9da7ea266ae479be8
+size 1353043968

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5c7cbf32da93989f14d9ba635e3e1d1ab2cc88a92908a5ed0f149375f6ee49
+size 1761962

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}