Fix vLLM (#41129) and TRT-LLM (#13559, #15110) references 73dd5da verified joerowell commited on 19 days ago
Model card: add license + Transformers/TRT-LLM deployment; add LICENSE.md 0b56e4c verified joerowell commited on 19 days ago
Fix gating: per-element to match g_proj weights (was True/per-head) (#1) 167da65 joerowell commited on 19 days ago