feat: update to DPO v6 merged model (BF16 safetensors) ffbdde5 verified intrect commited on 3 days ago
feat: update to DPO v4 merged model (SFT + DPO v4 language leak fix) c34c4f4 verified intrect commited on Feb 15
Fix config.json for vLLM compatibility (remove layer_types, fix rope_parameters) 7dc1232 verified intrect commited on Jan 28