bartowski/Vikhr-Nemo-12B-Instruct-R-21-09-24-GGUF

Same weights, converted vs Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160, lm_head 0/1

On the Hub · Downloads on Model Pulse