supergoose/tracking_shuffled_objects

1# tracking_shuffled_objects LoRA Models2 3This repository contains LoRA (Low-Rank Adaptation) models trained on the tracking_shuffled_objects dataset.4 5## Models in this repository:6 7- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0008_data_size1000_max_steps=500_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0008_data_size1000_max_steps=500_seed=1238- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr5e-05_data_size1000_max_steps=500_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr5e-05_data_size1000_max_steps=500_seed=1239- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=12310- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0004_data_size1000_max_steps=100_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0004_data_size1000_max_steps=100_seed=12311- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0002_data_size1000_max_steps=500_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0002_data_size1000_max_steps=500_seed=12312- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0008_data_size1000_max_steps=100_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0008_data_size1000_max_steps=100_seed=12313- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0002_data_size1000_max_steps=100_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0002_data_size1000_max_steps=100_seed=12314- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0006_data_size1000_max_steps=500_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0006_data_size1000_max_steps=500_seed=12315- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0003_data_size1000_max_steps=100_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0003_data_size1000_max_steps=100_seed=12316- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0004_data_size1000_max_steps=500_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0004_data_size1000_max_steps=500_seed=12317- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0005_data_size1000_max_steps=500_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0005_data_size1000_max_steps=500_seed=12318- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0003_data_size1000_max_steps=500_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0003_data_size1000_max_steps=500_seed=12319- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=100_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=100_seed=12320- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0005_data_size1000_max_steps=100_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0005_data_size1000_max_steps=100_seed=12321- `llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0006_data_size1000_max_steps=100_seed=123/`: LoRA adapter for llama_finetune_tracking_shuffled_objects_r16_alpha=32_dropout=0.05_lr0.0006_data_size1000_max_steps=100_seed=12322 23## Usage24 25To use these LoRA models, you'll need the `peft` library:26 27```bash28pip install peft transformers torch29```30 31Example usage:32 33```python34from peft import PeftModel35from transformers import AutoModelForCausalLM, AutoTokenizer36 37# Load base model38base_model_name = "your-base-model"  # Replace with actual base model39model = AutoModelForCausalLM.from_pretrained(base_model_name)40tokenizer = AutoTokenizer.from_pretrained(base_model_name)41 42# Load LoRA adapter43model = PeftModel.from_pretrained(44    model, 45    "supergoose/tracking_shuffled_objects",46    subfolder="model_name_here"  # Replace with specific model folder47)48 49# Use the model50inputs = tokenizer("Your prompt here", return_tensors="pt")51outputs = model.generate(**inputs)52```53 54## Training Details55 56- Dataset: tracking_shuffled_objects57- Training framework: LoRA/PEFT58- Models included: 15 variants59 60## Files Structure61 62Each model folder contains:63- `adapter_config.json`: LoRA configuration64- `adapter_model.safetensors`: LoRA weights65- `tokenizer.json`: Tokenizer configuration66- Additional training artifacts67 68---69*Generated automatically by LoRA uploader script*70