Upload 6 files

43ch/README.md

@@ -0,0 +1,203 @@
+---
+library_name: peft
+tags:
+- lora
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

43ch/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "TextToLatentRFDiT",
+    "parent_library": "irodori_tts.model"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32.0,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "wk",
+    "wo",
+    "wv",
+    "wq"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

43ch/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc10166d27b4a7b1defee3c77664ced749196d72062eaec88cfc583840b10f1
+size 6847184

43ch/ema_shadow.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d5d9103dc03853300da50d10c2782cfe68b8350832935ef40230859f1c4c73f
+size 13719297

43ch/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ca2ca9f6962dd73a72da87411292a803de2f6c32724e605b4422d0f40a7081
+size 13836619

43ch/train_state.json

@@ -0,0 +1,102 @@
+{
+  "step": 3000,
+  "base_model_path": "E:\\Emoji-TTS\\checkpoints\\Aratako_Irodori-TTS-500M-v2\\model.safetensors",
+  "base_model_sha256": "e5add885303babe328eae2c426475e41bc2f2aca2bcb010a2ceb6b6ddd1b8d9c",
+  "base_model_config": {
+    "latent_dim": 32,
+    "latent_patch_size": 1,
+    "model_dim": 1280,
+    "num_layers": 12,
+    "num_heads": 20,
+    "mlp_ratio": 2.875,
+    "text_mlp_ratio": 2.6,
+    "speaker_mlp_ratio": 2.6,
+    "dropout": 0.0,
+    "text_vocab_size": 99574,
+    "text_tokenizer_repo": "llm-jp/llm-jp-3-150m",
+    "text_add_bos": true,
+    "text_dim": 512,
+    "text_layers": 10,
+    "text_heads": 8,
+    "speaker_dim": 768,
+    "speaker_layers": 8,
+    "speaker_heads": 12,
+    "speaker_patch_size": 1,
+    "timestep_embed_dim": 512,
+    "adaln_rank": 192,
+    "norm_eps": 1e-05
+  },
+  "lora_config": {
+    "r": 16,
+    "lora_alpha": 32.0,
+    "lora_dropout": 0.05,
+    "target_modules": [
+      "wq",
+      "wk",
+      "wv",
+      "wo"
+    ]
+  },
+  "train_config": {
+    "manifest_path": "E:\\Emoji-TTS\\data\\train_manifest.jsonl",
+    "output_dir": "E:\\Emoji-TTS\\lora\\my_lora",
+    "batch_size": 4,
+    "num_workers": 2,
+    "dataloader_persistent_workers": false,
+    "dataloader_prefetch_factor": 2,
+    "allow_tf32": false,
+    "compile_model": false,
+    "learning_rate": 0.0001,
+    "weight_decay": 0.01,
+    "optimizer": "adamw",
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.999,
+    "adam_eps": 1e-08,
+    "muon_momentum": 0.95,
+    "muon_adjust_lr_fn": "match_rms_adamw",
+    "lr_scheduler": "none",
+    "warmup_steps": 0,
+    "caption_warmup": false,
+    "caption_warmup_steps": 0,
+    "stable_steps": 0,
+    "min_lr_scale": 0.1,
+    "max_steps": 3000,
+    "log_every": 10,
+    "save_every": 500,
+    "checkpoint_best_n": 0,
+    "valid_ratio": 0.1,
+    "valid_every": 100,
+    "progress": true,
+    "progress_all_ranks": false,
+    "precision": "bf16",
+    "grad_clip_norm": 1.0,
+    "gradient_accumulation_steps": 1,
+    "max_text_len": 256,
+    "max_caption_len": null,
+    "text_condition_dropout": 0.1,
+    "caption_condition_dropout": 0.1,
+    "speaker_condition_dropout": 0.1,
+    "max_latent_steps": 750,
+    "fixed_target_latent_steps": null,
+    "fixed_target_full_mask": false,
+    "timestep_logit_mean": 0.0,
+    "timestep_logit_std": 1.0,
+    "timestep_stratified": false,
+    "timestep_min": 0.001,
+    "timestep_max": 0.999,
+    "wandb_enabled": false,
+    "wandb_project": null,
+    "wandb_entity": null,
+    "wandb_run_name": null,
+    "wandb_mode": "online",
+    "ddp_find_unused_parameters": false,
+    "lora_enabled": false,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.0,
+    "lora_bias": "none",
+    "lora_target_modules": "diffusion_attn",
+    "seed": 0
+  },
+  "ema_decay": 0.9999
+}