mradermacher/polyglot-lion-0.6b-GGUF

Same weights, converted (fewer layers) vs knoveleng/polyglot-lion-0.6b. mradermacher/polyglot-lion-0.6b-GGUF matches part of knoveleng/polyglot-lion-0.6b (310 of its 611 tensors; the rest of knoveleng/polyglot-lion-0.6b has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse