nusa-id/tts-lora

README.md

@@ -0,0 +1,58 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: unsloth/csm-1b
+tags:
+- base_model:adapter:unsloth/csm-1b
+- lora
+- transformers
+- unsloth
+pipeline_tag: text-generation
+model-index:
+- name: outputs
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# outputs
+
+This model is a fine-tuned version of [unsloth/csm-1b](https://huggingface.co/unsloth/csm-1b) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 3407
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 5
+- training_steps: 500
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- PEFT 0.17.1
+- Transformers 4.52.3
+- Pytorch 2.8.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.4

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "CsmForConditionalGeneration",
+    "parent_library": "transformers.models.csm.modeling_csm",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/csm-1b",
+  "bias": "none",
+  "corda_config": null,
+  "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,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e878f024dfbf300346fdb769701cf22bdf0c5462bbbb4a11210eb5d841d1d95c
+size 116190168

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69283dc3056464b9e968cac020193142c7cc7633153531ae9a29fd673868191
+size 5649