mradermacher/AgentHijack-Agent-GGUF

Same weights, converted (fewer layers) vs TMLR-Group-HF/AgentHijack-Agent. mradermacher/AgentHijack-Agent-GGUF matches part of TMLR-Group-HF/AgentHijack-Agent (339 of its 729 tensors; the rest of TMLR-Group-HF/AgentHijack-Agent has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: MLP 0/84, Attention 0/196, Norms 0/57, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse