Epoch-3 full fine-tuning checkpoint in original LLaVA format. Load with the pinned TARS/LLaVA loader, not an HF LoRA loader. Paper profiles are reconstructions with documented assumptions, not author checkpoints.
Independent publisher
Pham Ba Cong
pbcong
Models in Library3
Datasets in Library0
Models on Hugging Face35
Followers6
Compare the published evidence
This profile connects the 3 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
Epoch-1 full fine-tuning checkpoint in original LLaVA format. Load with the pinned TARS/LLaVA loader, not an HF LoRA loader. Paper profiles are reconstructions with documented assumptions, not author checkpoints.
Epoch-2 full fine-tuning checkpoint in original LLaVA format. Load with the pinned TARS/LLaVA loader, not an HF LoRA loader. Paper profiles are reconstructions with documented assumptions, not author checkpoints.