legraphista/xLAM-8x7b-r-IMat-GGUF
Same weights, converted vs Salesforce/xLAM-8x7b-r. Same weights stored in another dtype (BF16 → F16/F32), plus 96 new tensors.
Tensors changed: Embeddings 0/1, other 0/32, Norms 0/65, Attention 0/128, lm_head 0/1
Same weights, converted vs Salesforce/xLAM-8x7b-r. Same weights stored in another dtype (BF16 → F16/F32), plus 96 new tensors.
Tensors changed: Embeddings 0/1, other 0/32, Norms 0/65, Attention 0/128, lm_head 0/1