mradermacher/PULSE-7bv5-GGUF
Same weights, converted vs OpenMEDLab/PULSE-7bv5. Same weights stored in another dtype (BF16 → F16/F32), plus 2 new tensors.
Tensors changed: Norms 0/122, MLP 0/120, Attention 0/60, Embeddings 0/1, lm_head 0/1
Same weights, converted vs OpenMEDLab/PULSE-7bv5. Same weights stored in another dtype (BF16 → F16/F32), plus 2 new tensors.
Tensors changed: Norms 0/122, MLP 0/120, Attention 0/60, Embeddings 0/1, lm_head 0/1