mradermacher/starcoder2-3b-instruct-GGUF
Same weights, converted vs zzzmahesh/starcoder2-3b-instruct. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/122, MLP 0/120, Attention 0/240
Same weights, converted vs zzzmahesh/starcoder2-3b-instruct. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/122, MLP 0/120, Attention 0/240