GitHub - sugeerth/gpu-training-notebooks: Multi-GPU Training Notebooks: DPO, LoRA, RLHF, Diffusion, Audio, Vision

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 8 Commits
.github/workflows		.github/workflows
.gitignore		.gitignore
Colab_Pro_A100_Max_Training.ipynb		Colab_Pro_A100_Max_Training.ipynb
DPO_Training.ipynb		DPO_Training.ipynb
Distributed_Training_DeepSpeed.ipynb		Distributed_Training_DeepSpeed.ipynb
Free_Distributed_SFT_DPO.ipynb		Free_Distributed_SFT_DPO.ipynb
GRPO_Reasoning_Training.ipynb		GRPO_Reasoning_Training.ipynb
LLM_as_Judge_Evaluation.ipynb		LLM_as_Judge_Evaluation.ipynb
LoRA_QLoRA_FineTuning.ipynb		LoRA_QLoRA_FineTuning.ipynb
Modern_Full_FineTuning_PostTraining.ipynb		Modern_Full_FineTuning_PostTraining.ipynb
Multimodal_LoRA_QLoRA_DPO.ipynb		Multimodal_LoRA_QLoRA_DPO.ipynb
PostTraining_Core_Understanding.ipynb		PostTraining_Core_Understanding.ipynb
Simple_MultiGPU_ActualTraining.ipynb		Simple_MultiGPU_ActualTraining.ipynb
Simple_MultiGPU_Alignment_Showdown.ipynb		Simple_MultiGPU_Alignment_Showdown.ipynb
Simple_MultiGPU_Audio.ipynb		Simple_MultiGPU_Audio.ipynb
Simple_MultiGPU_Benchmark.ipynb		Simple_MultiGPU_Benchmark.ipynb
Simple_MultiGPU_DPO_RLHF.ipynb		Simple_MultiGPU_DPO_RLHF.ipynb
Simple_MultiGPU_Diffusion.ipynb		Simple_MultiGPU_Diffusion.ipynb
Simple_MultiGPU_ImageClassification.ipynb		Simple_MultiGPU_ImageClassification.ipynb
Simple_MultiGPU_LLM_Judge.ipynb		Simple_MultiGPU_LLM_Judge.ipynb
Simple_MultiGPU_Multimodal.ipynb		Simple_MultiGPU_Multimodal.ipynb
Simple_MultiGPU_Training.ipynb		Simple_MultiGPU_Training.ipynb
Simple_MultiGPU_VLM_Judge.ipynb		Simple_MultiGPU_VLM_Judge.ipynb
dpo_results.json		dpo_results.json
dpo_train.py		dpo_train.py
index.html		index.html
requirements.txt		requirements.txt