open-inference/Kimi-K3-W4A8-K512-DenseChannel-GPTQ-Cal128-v2 Feature Extraction • 2.8T • Updated 3 days ago • 57
open-inference/Kimi-K3-W4A8-K512-DenseChannel-GPTQ-Cal128-v2 Feature Extraction • 2.8T • Updated 3 days ago • 57
open-inference/Kimi-K3-W4A8-K512-GPTQ-Mixed-Cal72-Seq1024 Feature Extraction • 2.8T • Updated 11 days ago • 215
open-inference/Kimi-K3-W4A8-K512-GPTQ-Mixed-Cal72-Seq1024 Feature Extraction • 2.8T • Updated 11 days ago • 215
Running 602 Scaling test-time compute 📈 602 Boost LLM answers with flexible test‑time search strategies
Reward models on the hub Collection UNMAINTAINED: See RewardBench... A place to collect reward models, an often not released artifact of RLHF. • 18 items • Updated Apr 13, 2024 • 25