Commit History

fix(rope): YaRN attention_factor is (0.1*ln(factor)+1)*attn_factor, not the bare multiplier
444b2a1
verified

joerowell commited on

README: require vLLM #47311 for tool calling; glm47 parser fallback on older builds
07133fb
verified

joerowell commited on

Update chat_template.jinja
afa9793
verified

joerowell commited on

Fix sliding-window RoPE and expert loading for trust_remote_code
a156999
verified

joerowell commited on