mradermacher/DrMedra4B-abliterated-GGUF

Same weights, converted (fewer layers) vs drwlf/DrMedra4B-abliterated. mradermacher/DrMedra4B-abliterated-GGUF matches part of drwlf/DrMedra4B-abliterated (445 of its 884 tensors; the rest of drwlf/DrMedra4B-abliterated has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136, lm_head 0/1

On the Hub · Downloads on Model Pulse