Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,136 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: outputs/Simp_22_1_2026
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.8.0`
+```yaml
+base_model: /root/anhnct/Spark-TTS-finetune/extend_vocab_pretrained/LLM
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+trust_remote_code: true
+
+strict: false
+
+datasets:
+  - path: .
+    data_files: ["/root/anhnct/Spark-TTS-finetune/PROMPTS/product_ft_data/elevenlab_dataset_3.jsonl", "/root/anhnct/Spark-TTS-finetune/PROMPTS/product_ft_data/elevenlab_dataset_4.jsonl", "/root/anhnct/Spark-TTS-finetune/PROMPTS/product_ft_data/elevenlab_dataset_reflex.jsonl", "/root/anhnct/Spark-TTS-finetune/PROMPTS/product_ft_data/elevenlab_slow.jsonl", "/root/anhnct/Spark-TTS-finetune/PROMPTS/product_ft_data/hf_song_ngu.jsonl", "/root/anhnct/Spark-TTS-finetune/PROMPTS/product_ft_data/LibriTTS.jsonl"]
+    type: completion
+    
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./outputs/Simp_22_1_2026
+
+
+sequence_len: 2048
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: true
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 8
+num_epochs: 10
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: true
+
+gradient_checkpointing: false
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 50
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 1
+save_steps: 10000
+save_total_limit: 100
+debug:
+deepspeed:
+weight_decay: 0.0
+
+```
+
+</details><br>
+
+# outputs/Simp_22_1_2026
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.3568
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| No log        | 0.0005 | 1     | 5.6361          |
+| 4.5777        | 1.0    | 2216  | 5.3235          |
+| 4.5116        | 2.0    | 4432  | 5.3313          |
+| 4.4611        | 3.0    | 6648  | 5.3390          |
+| 4.4496        | 4.0    | 8864  | 5.3471          |
+| 4.4141        | 5.0    | 11080 | 5.3521          |
+| 4.4031        | 6.0    | 13296 | 5.3541          |
+| 4.4174        | 7.0    | 15512 | 5.3562          |
+| 4.4071        | 8.0    | 17728 | 5.3561          |
+| 4.4179        | 9.0    | 19944 | 5.3567          |
+| 4.3882        | 10.0   | 22160 | 5.3568          |
+
+
+### Framework versions
+
+- Transformers 4.50.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.4

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 165167
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "transformers_version": "4.50.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d6d41b3696b398d96de5f74b58abddf394dc8ac57446f35ebbfb357691deb45
+size 1011807800

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e754b7a11590bc1467423e545a4bdc824009e387f81ac6d7bc30b23c06accefd
+size 14130827