Gleb

hurrricane8's activity

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

upvoted a collection 29 days ago

HARP Quantized Models

Collection

Quantized Llama 2 (7B/13B/70B) at 2-bit via HARP, a learnable orthogonal preprocessor for extreme LLM quantization. EMNLP 2026. • 3 items • Updated about 1 month ago • 1

upvoted a paper 30 days ago

HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization

Paper • 2605.29843 • Published May 28 • 2

updated 3 models about 1 month ago

brain-lab/Llama-2-70b-QuIP-HARP-2Bit

Text Generation • 3B • Updated about 1 month ago • 62

brain-lab/Llama-2-13b-QuIP-HARP-2Bit

Text Generation • 0.9B • Updated about 1 month ago • 59

brain-lab/Llama-2-7b-QuIP-HARP-2Bit

Text Generation • 0.6B • Updated about 1 month ago • 59

upvoted a paper 3 months ago

One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining

Paper • 2606.30634 • Published Jun 29 • 24