ENTITY
Sherry
Sherry
PulseAugur coverage of Sherry — every cluster mentioning Sherry across labs, papers, and developer communities, ranked by signal.
Total · 30d
2
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
1
1 over 90d
TIER MIX · 90D
TOPICS
TIMELINE
- 2026-09-29 product_launch Precisit released a 1.6 MB model using Sherry's 3:4 ternary format that plays Connect Four. source
SENTIMENT · 30D
1 day(s) with sentiment data
RECENT · PAGE 1/1 · 2 TOTAL
-
Tiny 1.6MB model plays Connect Four with 1.375 bits/weight
Precisit has developed a 1.6 MB model that plays Connect Four with performance comparable to its 7.8 MB int8 version. This new model utilizes Sherry's 3:4 ternary format, achieving 1.375 bits per weight, and runs effici…
-
Native low-bit LLM architectures outperform post-training compression
The article argues that post-training compression techniques for large language models are fundamentally flawed. It explains that these methods, which attempt to reduce model size by quantizing weights after training, f…