ai-sage/GigaChat-20B-A3B-instruct-bf16

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

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/2829, Attention 0/112, lm_head 0/1

2 derivatives checked

• mradermacher/GigaChat-20B-A3B-instruct-bf16-i1-GGUF: Quantization
• mradermacher/GigaChat-20B-A3B-instruct-bf16-GGUF: Quantization

On the Hub · Downloads on Model Pulse