mradermacher/teeny-tiny-mixtral-GGUF
Same weights, converted vs arcee-ai/teeny-tiny-mixtral. Same weights stored in another dtype (F32 → F16/F32), plus 6 new tensors.
Tensors changed: Embeddings 0/1, other 0/2, Attention 0/8, Norms 0/5, lm_head 0/1
Same weights, converted vs arcee-ai/teeny-tiny-mixtral. Same weights stored in another dtype (F32 → F16/F32), plus 6 new tensors.
Tensors changed: Embeddings 0/1, other 0/2, Attention 0/8, Norms 0/5, lm_head 0/1