Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
Paper • 2411.17691 • Published • 13 •
5
Tao Ge
sggetao
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
Synthetic Computers at Scale for Long-Horizon Productivity Simulation upvoted a paper 8 months ago
QueST: Incentivizing LLMs to Generate Difficult Problems authored a paper over 1 year ago
Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for
Quantized LLMs with 100T Training TokensOrganizations
None yet
