gaianet/xLAM-8x22b-r-GGUF
Same weights, converted vs Salesforce/xLAM-8x22b-r. Same weights stored in another dtype (BF16 → F16/F32), plus 168 new tensors.
Tensors changed: Embeddings 0/1, other 0/56, Attention 0/224, Norms 0/113, lm_head 0/1
Same weights, converted vs Salesforce/xLAM-8x22b-r. Same weights stored in another dtype (BF16 → F16/F32), plus 168 new tensors.
Tensors changed: Embeddings 0/1, other 0/56, Attention 0/224, Norms 0/113, lm_head 0/1