mradermacher/dggirl-gemma-4-E4B-it-merged-GGUF

Same weights, converted (fewer layers) vs JeanLima2024/dggirl-gemma-4-E4B-it-merged. mradermacher/dggirl-gemma-4-E4B-it-merged-GGUF matches part of JeanLima2024/dggirl-gemma-4-E4B-it-merged (677 of its 2130 tensors; the rest of JeanLima2024/dggirl-gemma-4-E4B-it-merged has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), plus 43 new tensors.

Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168

On the Hub · Downloads on Model Pulse