DevQuasar-8/bigcode.starcoder2-15b-GGUF
Same weights, converted vs bigcode/starcoder2-15b. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/162, MLP 0/160, Attention 0/320, lm_head 0/1
Same weights, converted vs bigcode/starcoder2-15b. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/162, MLP 0/160, Attention 0/320, lm_head 0/1