🔄 In a Training Loop
RuAR
RachidAR
AI & ML interests
1.58 bit LLM
Recent Activity
liked a model 14 days ago
prism-ml/Ternary-Bonsai-27B-gguf liked a model 26 days ago
Patil/Krea-2-depth-controlnet liked a model 28 days ago
Comfy-Org/Ideogram-4Organizations
-
Addition is All You Need for Energy-efficient Language Models
Paper • 2410.00907 • Published • 151 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 629 -
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Paper • 2404.16710 • Published • 82 -
Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory
Paper • 2405.08707 • Published • 34
by @RachidAR
-
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 629 -
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 191 -
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Paper • 2402.19427 • Published • 59 -
ResLoRA: Identity Residual Mapping in Low-Rank Adaption
Paper • 2402.18039 • Published • 11
by @RachidAR
-
Addition is All You Need for Energy-efficient Language Models
Paper • 2410.00907 • Published • 151 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 629 -
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Paper • 2404.16710 • Published • 82 -
Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory
Paper • 2405.08707 • Published • 34
-
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 629 -
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 191 -
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Paper • 2402.19427 • Published • 59 -
ResLoRA: Identity Residual Mapping in Low-Rank Adaption
Paper • 2402.18039 • Published • 11