mradermacher/WR30a-Deep-7B-0711-GGUF

Same weights, converted (fewer layers) vs prithivMLmods/WR30a-Deep-7B-0711. mradermacher/WR30a-Deep-7B-0711-GGUF matches part of prithivMLmods/WR30a-Deep-7B-0711 (339 of its 729 tensors; the rest of prithivMLmods/WR30a-Deep-7B-0711 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1

On the Hub · Downloads on Model Pulse