mradermacher/gemma-3n-E2B-it-absolute-heresy-GGUF

Same weights, converted (fewer layers) vs MuXodious/gemma-3n-E2B-it-absolute-heresy. mradermacher/gemma-3n-E2B-it-absolute-heresy-GGUF matches part of MuXodious/gemma-3n-E2B-it-absolute-heresy (694 of its 1556 tensors; the rest of MuXodious/gemma-3n-E2B-it-absolute-heresy has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), plus 32 new tensors.

Tensors changed: Embeddings 0/1, other 0/211, Norms 0/272, MLP 0/90, Attention 0/120

On the Hub · Downloads on Model Pulse