The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits (2402.17764)

Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs). In this work, we introduce a 1-bit LLM variant, namely BitNet b1.58, in which every single parameter (or weight) of the LLM is ternary {-1, 0, 1}. It matches the full-precision (i.e., FP16 or BF16) Transformer LLM with the same model size and training tokens in terms of both perplexity and end-task performance, while being significantly more cost-effective in terms of latency, memory, throughput, and energy consumption. More profoundly, the 1.58-bit LLM defines a new scaling law and recipe for training new generations of LLMs that are both high-performance and cost-effective. Furthermore, it enables a new computation paradigm and opens the door for designing specific hardware optimized for 1-bit LLMs.

New activity in sentence-transformers/embeddings-semantic-search about 1 year ago

Fix typos in app.py

#1 opened about 1 year ago by

northern-64bit

New activity in microsoft/LLMLingua about 1 year ago

Clarify and Correct Errors in Sentence on Line 24 in app.py

#1 opened about 1 year ago by

northern-64bit

liked a Space about 1 year ago

120

LLMLingua

📝

Compress prompts to speed up language models!