PEFT
Safetensors
English
audio-language-model
audio-question-answering
lora
mizar
rt-opd
knowledge-distillation
Instructions to use KaiyangLi/Mizar-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use KaiyangLi/Mizar-3B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("KE-Team/Ke-Omni-R-3B") model = PeftModel.from_pretrained(base_model, "KaiyangLi/Mizar-3B") - Notebooks
- Google Colab
- Kaggle
Download CHECKPOINT_PROVENANCE.json from KaiyangLi/Mizar-3B: direct link, hf CLI and curl.
- Browser
- Download file 696 Bytes
-
https://huggingface.co/KaiyangLi/Mizar-3B/resolve/main/CHECKPOINT_PROVENANCE.json
- Command line
-
hf download hf://KaiyangLi/Mizar-3B/CHECKPOINT_PROVENANCE.json
-
curl -L -o CHECKPOINT_PROVENANCE.json https://huggingface.co/KaiyangLi/Mizar-3B/resolve/main/CHECKPOINT_PROVENANCE.json
696 Bytes
| { | |
| "seed": 85, | |
| "step": 626, | |
| "selection": "Highest post-hoc Macro-3 among fixed step626 Ke main seeds82-86; paper reports all seeds", | |
| "original_checkpoint_manifest_sha256": "b8b87e3cf85fe673813297ea2e6d7d580e9d29c2ef313a19cc4a43ec4677be69", | |
| "original_adapter_config_sha256": "25c19fc2904dd1e09c7cc11a92c4324176da917f8ca220b838c8d6ed989bbf30", | |
| "adapter_model_sha256": "c53a801a364b714f5bd351a9b5bec292676c1b37253197b7e92121e08f0215de", | |
| "config_portability_changes": [ | |
| "base_model_name_or_path", | |
| "revision" | |
| ], | |
| "base_model_revision": "54a602334a1379d9321cf26db6982e29f25bfeaf", | |
| "original_launch_sha256": "1c9a34c4230888818a3a7365e240b9405ee563f7bf64e107370a70dce8c2a1f9" | |
| } | |