mradermacher/Qwen2.5-0.5B-Instruct-3MPER0RR-abliterated-GGUF

Same weights, converted vs 3MPER0RR/Qwen2.5-0.5B-Instruct-3MPER0RR-abliterated. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168

On the Hub · Downloads on Model Pulse