mradermacher/TinyMistral-6x248M-GGUF
Same weights, converted vs M4-ai/TinyMistral-6x248M. Same weights stored in another dtype (F32 → F16/F32), plus 36 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, other 0/12, Norms 0/25, Attention 0/48
Same weights, converted vs M4-ai/TinyMistral-6x248M. Same weights stored in another dtype (F32 → F16/F32), plus 36 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, other 0/12, Norms 0/25, Attention 0/48