Rush Tabesh

soroushtabesh's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper about 2 months ago

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training

Paper • 2510.18784 • Published Oct 21 • 1

upvoted a paper 3 months ago

Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization

Paper • 2509.23202 • Published Sep 27 • 27

upvoted a paper 5 months ago

The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm

Paper • 2507.18553 • Published Jul 24 • 40

upvoted a paper 7 months ago

SVD-Free Low-Rank Adaptive Gradient Optimization for Large Language Models

Paper • 2505.17967 • Published May 23 • 17

authored a paper 7 months ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published May 20 • 78

published a model 9 months ago

soroushtabesh/QuEST-1.1B-INT4-test

Updated Mar 19

authored a paper 11 months ago

RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation

Paper • 2401.04679 • Published Jan 9, 2024 • 2

upvoted a paper 11 months ago

HALO: Hadamard-Assisted Lossless Optimization for Efficient Low-Precision LLM Training and Fine-Tuning

Paper • 2501.02625 • Published Jan 5 • 15

authored a paper 11 months ago

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations

Paper • 2502.05003 • Published Feb 7 • 42

upvoted a paper 11 months ago

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations

Paper • 2502.05003 • Published Feb 7 • 42

authored a paper 12 months ago

HALO: Hadamard-Assisted Lossless Optimization for Efficient Low-Precision LLM Training and Fine-Tuning

Paper • 2501.02625 • Published Jan 5 • 15

upvoted a paper almost 2 years ago

RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation

Paper • 2401.04679 • Published Jan 9, 2024 • 2

upvoted a paper about 2 years ago

QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models

Paper • 2310.16795 • Published Oct 25, 2023 • 27

liked a dataset over 2 years ago

garage-bAInd/Open-Platypus

Viewer • Updated Jan 24, 2024 • 24.9k • 4.27k • 412

New activity in garage-bAInd/Open-Platypus over 2 years ago

Determining source content

5

#3 opened over 2 years ago by

M-Chimiste

liked a Space over 2 years ago

Running on CPU Upgrade

13.8k

Open LLM Leaderboard

🏆

13.8k

Track, rank and evaluate open LLMs and chatbots