The Differences Between Direct Alignment Algorithms are a Blur
Paper
β’
2502.01237
β’
Published
β’
112
Junlin Zhou
jlzhou
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 12 hours ago
The Differences Between Direct Alignment Algorithms are a Blur
updated
a model
1 day ago
tablegpt/TableGPT2-7B
updated
a collection
1 day ago
TableGPT2
Organizations
jlzhou's activity
upvoted
a
paper
about 12 hours ago
updated
a
model
1 day ago
updated
a
collection
1 day ago
commented
a
paper
3 days ago
reacted to
schuler's
post with π
3 days ago
Post
7132
π’ New Research Alert: Making Language Models Smaller & Smarter!
Thrilled to share the latest technical report demonstrating how to reduce language model parameters by 77% while maintaining performance.
The secret? Grouped pointwise convolutions. Yes. We brought a method from computer vision to the transformers arena.
π Key Findings:
β’ 77% parameter reduction.
β’ Maintained model capabilities.
β’ Improved generalization.
Paper: https://www.researchgate.net/publication/388835829_SAVING_77_OF_THE_PARAMETERS_IN_LARGE_LANGUAGE_MODELS_TECHNICAL_REPORT
Code: https://github.com/joaopauloschuler/less-parameters-llm
Thrilled to share the latest technical report demonstrating how to reduce language model parameters by 77% while maintaining performance.
The secret? Grouped pointwise convolutions. Yes. We brought a method from computer vision to the transformers arena.
π Key Findings:
β’ 77% parameter reduction.
β’ Maintained model capabilities.
β’ Improved generalization.
Paper: https://www.researchgate.net/publication/388835829_SAVING_77_OF_THE_PARAMETERS_IN_LARGE_LANGUAGE_MODELS_TECHNICAL_REPORT
Code: https://github.com/joaopauloschuler/less-parameters-llm
- 2 replies
upvoted
an
article
3 days ago
Article
DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
By
β’
β’
25
updated
a
model
6 days ago
liked
a
Space
7 days ago
Adding Evaluation Results
#1 opened 7 days ago
by
jlzhou
published
an
article
7 days ago
Article
Distributed SFT with trl and DeepSpeed Part 2: Scaling Locally
By
β’
β’
1
liked
a
model
9 days ago
updated
a
model
9 days ago
published
a
model
9 days ago
liked
a
model
9 days ago
upvoted
a
paper
9 days ago
liked
a
dataset
9 days ago
upvoted
a
paper
19 days ago
upvoted
3
papers
21 days ago
Better & Faster Large Language Models via Multi-token Prediction
Paper
β’
2404.19737
β’
Published
β’
76
Training Large Language Models to Reason in a Continuous Latent Space
Paper
β’
2412.06769
β’
Published
β’
78
Enhancing Training Efficiency Using Packing with Flash Attention
Paper
β’
2407.09105
β’
Published
β’
15