Balancing Speed and Stability: The Trade-offs of FP8 vs. BF16 Training in LLMs
Paper
•
2411.08719
•
Published
•
1
AI & ML interests
Formerly, MDEL, we have renamed ourselves after the model we deployed, Aurora-M. Visit us here: https://huggingface.co/aurora-m
Recent Activity
View all activity
kazukifujii
authored
a
paper
3 days ago
terryyz
authored
8
papers
8 days ago
DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text
Paper
•
2306.05540
•
Published
Pop Quiz! Do Pre-trained Code Models Possess Knowledge of Correct API Names?
Paper
•
2309.07804
•
Published
•
2
Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order
Paper
•
2404.00399
•
Published
•
43
XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts
Paper
•
2404.15247
•
Published
•
3
Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity
Paper
•
2301.12867
•
Published
GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models
Paper
•
2411.05830
•
Published
•
22
FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing
Paper
•
2305.17497
•
Published
Rethinking Round-Trip Translation for Machine Translation Evaluation
Paper
•
2209.07351
•
Published
Taishi-N324
authored
a
paper
8 days ago
terryyz
authored
a
paper
8 days ago
teknium
authored
2
papers
9 days ago
Ziyang
authored
a
paper
14 days ago
terryyz
authored
a
paper
29 days ago
Ziyang
authored
a
paper
about 2 months ago
rootacess
authored
a
paper
about 2 months ago
Ziyang
authored
3
papers
about 2 months ago