Downloads · 30 days
14
6% of all-time downloads
acchead-llama2-chat-7bx70b
hacky/acchead-llama2-chat-7bx70b
acchead-llama2-chat-7bx70b is a machine learning model from hacky. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
The Acceptance Prediction Head for Llama-2-chat 7B and 70B model pair trained with weightmismatch=6 and resnetnumlayers=3. It is recommended to be used with stopthreshold=0.7. See arxiv: 2405.19715 for more details.
All-time downloads
246
Public
Repo size
67.2 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin67.2 MB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Jul 9, 2024
- Updated
- Jul 29, 2024
- SHA
- 8d2795f5
Model card
From the Hugging Face model README
The Acceptance Prediction Head for Llama-2-chat 7B and 70B model pair trained with weight_mismatch=6 and resnet_num_layers=3. It is recommended to be used with stop_threshold=0.7. See arxiv: 2405.19715 for more details.
Usage: GitHub
Citation
@article{huang2024specdec++,
title={SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths},
author={Huang, Kaixuan and Guo, Xudong and Wang, Mengdi},
journal={arXiv preprint arXiv:2405.19715},
year={2024}
}
- Library
- transformers
- License
- apache-2.0
- Created
- Jul 9, 2024
- Updated
- Jul 29, 2024