prajwalJumde/orpheus_tts_FT_may13

.gitattributes

@@ -37,3 +37,4 @@ unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text
 unsloth.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
 unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,10 +1,8 @@
 ---
-base_model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
 library_name: peft
-license: llama3.1
+license: apache-2.0
+base_model: unsloth/orpheus-3b-0.1-ft
 tags:
-- trl
-- sft
 - unsloth
 - generated_from_trainer
 model-index:
@@ -17,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # outputs
 
-This model is a fine-tuned version of [unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit) on an unknown dataset.
+This model is a fine-tuned version of [unsloth/orpheus-3b-0.1-ft](https://huggingface.co/unsloth/orpheus-3b-0.1-ft) on an unknown dataset.
 
 ## Model description
 
@@ -36,16 +34,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 2
+- learning_rate: 0.0001
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 3407
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 2
 - total_train_batch_size: 8
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 5
-- training_steps: 60
+- optimizer: Use OptimizerNames.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_ratio: 0.03
+- training_steps: 500
 
 ### Training results
 
@@ -53,8 +51,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.12.0
-- Transformers 4.44.2
-- Pytorch 2.4.0+cu121
-- Datasets 2.21.0
-- Tokenizers 0.19.1
+- PEFT 0.15.2
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -1,8 +1,11 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit",
+  "base_model_name_or_path": "unsloth/orpheus-3b-0.1-ft",
   "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -10,25 +13,27 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0,
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "down_proj",
-    "gate_proj",
-    "k_proj",
-    "q_proj",
     "o_proj",
-    "up_proj"
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
   "use_dora": false,
-  "use_rslora": false
+  "use_rslora": true
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f916ae7695de68664c5ac90b080d61fe1e0ebbc6872834236524888109ecda
-size 167832240
+oid sha256:3f9fe50dcaa23a9c0908e0f55beb51dfb70a646c785d72d27d6fe4d50a4abf99
+size 778096664

special_tokens_map.json

@@ -1,5 +1,26 @@
 {
-  "bos_token": "<|begin_of_text|>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<|finetune_right_pad_id|>"
+  "additional_special_tokens": [
+    "<|audio|>"
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cffb4ed4dd7e5a5f95197ec864219e711afec7f455b85a7169aaafc230c84d7
-size 5112
+oid sha256:6a09fba46486dd5351bec3e0b3b1a45731e60675a1a46a12ae2ef70cf91480ac
+size 5240