mradermacher/Codestral-22B-v0.1-abliterated-v3-GGUF
Quantization vs failspy/Codestral-22B-v0.1-abliterated-v3. mradermacher/Codestral-22B-v0.1-abliterated-v3-GGUF is a GGUF quantization (Q8_0) of the same weights: 113 tensors match exactly and 394 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/168, Attention 0/224, lm_head 0/1