llm-playground — rendered notebooks

34 notebooks across 7 directories. Auto-generated by the render-notebooks GitHub Actions workflow.

notebooks/Alpaca-CoT

• 01_test_finetune
• 01_test_finetune_upload
• 02_test_wandb_Colab_OOM
• 03_test_merge
• 04_test_resume
• 04_test_resume_pr

notebooks/axolotl/colab

• axolotl-falcon-40b-qlora-prepare_ds_only
• axolotl-falcon-gpt4-cleaned
• axolotl_falcon_1b_qlora_gsm8k
• axolotl_flash_optimum_qlora
• deepspeed_axolotl
• monkeypatch_axolotl
• nvitop
• qlora-falcon-guanaco
• qlora-falcon-hello
• runpod_serverless_minotaur

notebooks/axolotl/lambdalabs

• axolotl_falcon_1b_qlora_gsm8k

notebooks/axolotl/runpod

• axolotl-falcon-1b-qlora-gsm8k
• axolotl-falcon-1b-qlora-tutorial
• axolotl-falcon-40b-qlora-deepspeed
• axolotl-falcon-40b-qlora-gsm8k
• axolotl-falcon-7b-ft-gpt4-cleaned
• axolotl-falcon-7b-qlora-gsm8k
• axolotl-falcon-gpt4-cleaned
• axolotl-huggyllama-qlora-gsm8k
• axolotl-openllama-gsm8k

notebooks/datasets

• load_local_dataset_from_dir
• try_argilla
• try_spotlight_meerkat

notebooks/helper

• test_download
• test_download_huge
• test_upload

notebooks/text-generation-webui

• Colab_LoRA_training
• test_lora