Instructions to use SNUMPR/vlm_policy_init_7b_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use SNUMPR/vlm_policy_init_7b_lora with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
| {"run_name": "/dataset/llms/LLaVA_RLHF/LLaVA_Video-RLHF/pretrained/LLaVA_Video-RL-INIT-13bv2s2l_dv1-v1.5-336-lora-padding", "train_runtime": 13253.0183, "train_samples_per_second": 2.186, "train_steps_per_second": 0.017, "train_loss": 1.4022162783462389, "epoch": 1.0, "eval_loss": 1.417236328125, "eval_runtime": 341.5207, "eval_samples_per_second": 2.998, "eval_steps_per_second": 0.047} |