mradermacher/qwen2-vl-2b-abliterated-GGUF

Same weights, converted (fewer layers) vs MahdiAlikhah/qwen2-vl-2b-abliterated. mradermacher/qwen2-vl-2b-abliterated-GGUF matches part of MahdiAlikhah/qwen2-vl-2b-abliterated (338 of its 729 tensors; the rest of MahdiAlikhah/qwen2-vl-2b-abliterated has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse