mradermacher/Cerebras-GPT-111M-instruction-GGUF
Same weights, converted vs SebastianSchramm/Cerebras-GPT-111M-instruction. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Attention 0/20, Norms 0/42, MLP 0/20, Embeddings 0/2
Same weights, converted vs SebastianSchramm/Cerebras-GPT-111M-instruction. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Attention 0/20, Norms 0/42, MLP 0/20, Embeddings 0/2