ertghiu256/ministral-3-3b-glm-distillation-gguf

Same weights, converted (fewer layers) vs ertghiu256/ministral-3-3b-glm-distillation. ertghiu256/ministral-3-3b-glm-distillation-gguf matches part of ertghiu256/ministral-3-3b-glm-distillation (236 of its 458 tensors; the rest of ertghiu256/ministral-3-3b-glm-distillation has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/104

On the Hub · Downloads on Model Pulse