mradermacher/Maistros-8B-Instruct-GGUF

Same weights, converted (fewer layers) vs IMISLab/Maistros-8B-Instruct. mradermacher/Maistros-8B-Instruct-GGUF matches part of IMISLab/Maistros-8B-Instruct (309 of its 531 tensors; the rest of IMISLab/Maistros-8B-Instruct has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/69, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse