PEFT Method Comparison
⚖
Explore model performance with interactive Pareto plots
Benjamin Bossan
BenjaminB
AI & ML interests
None yet
Recent Activity
updated a Space about 13 hours ago
peft-internal-testing/PEFT-method-comparison-embed updated a Space about 13 hours ago
peft-internal-testing/PEFT-method-comparison new activity about 13 hours ago
peft-internal-testing/benchmark-graveyard:Add superseded/exploratory MonteCLoRA resultsOrganizations
updated 2
Spaces about 13 hours ago
Add superseded/exploratory MonteCLoRA results
1
#13 opened 1 day ago
by 
Sergasgr
Add superseded/exploratory BD-LoRA results
1
#12 opened 1 day ago
by Sergasgr
upvoted an article 2 days ago
Article
Transformers now runs llama.cpp quants
- +1
marcsun13, ArthurZ, lysandre
• • 58 Add superseded/exploratory VeLoRA results
1
#11 opened 6 days ago
by Sergasgr
updated a
model 3 days ago
updated a
Space 8 days ago
Add exploratory AdaMSS use_asa=True results (final_warmup=600 and final_warmup=1000)
1
#9 opened 16 days ago
by Sergasgr
Add superseded/exploratory UniLoRA results
1
#10 opened 10 days ago
by Sergasgr
Add superseded/exploratory BEFT and HiRA results
3
#7 opened 20 days ago
by Sergasgr
commented on Beyond LoRA: Can you beat the most popular fine-tuning technique? about 1 month ago
We only included techniques that are implemented in PEFT, and those two are not implemented.
commented 8
papers about 2 months ago
LoRA-FA: Memory-efficient Low-rank Adaptation for Large Language Models Fine-tuning
Paper • 2308.03303 • Published • 4 •
2
LoRA+: Efficient Low Rank Adaptation of Large Models
Paper • 2402.12354 • Published • 8 •
3
VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
Paper • 2405.17991 • Published • 14 •
5
Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation
Paper • 2411.04358 • Published •
1
Block-Diagonal LoRA for Eliminating Communication Overhead in Tensor Parallel LoRA Serving
Paper • 2510.23346 • Published •
1
LoRA-GA: Low-Rank Adaptation with Gradient Approximation
Paper • 2407.05000 • Published •
1
LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models
Paper • 2310.08659 • Published • 30 •
5
A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA
Paper • 2312.03732 • Published • 13 •
1