ai-sage/GigaChat-20B-A3B-instruct-GGUF

Same weights, converted vs ai-sage/GigaChat-20B-A3B-instruct. Same weights stored in another dtype (F32 → BF16/F32), plus 81 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/111, Attention 0/112, lm_head 0/1

On the Hub · Downloads on Model Pulse