YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
Llama3.2-1B-summary-length-exp2 - AWQ
- Model creator: https://huggingface.co/amang1802/
- Original model: https://huggingface.co/amang1802/Llama3.2-1B-summary-length-exp2/
Original model description:
library_name: transformers tags: []
Model Card for Model ID
- Summary Length PPO experiment #2
- No KL divergence in loss
Model Details
- Dataset size: 1024
- Epochs: 2
- Batch Size: 4 * 8 (using Grad Accu)
Optimizer args: Torch AdamW default, except
- LR = 0.0001
- Downloads last month
- 4