mradermacher/Hercules-Mini-1.8B-GGUF
Same weights, converted vs M4-ai/Hercules-Mini-1.8B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168, lm_head 0/1
Same weights, converted vs M4-ai/Hercules-Mini-1.8B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168, lm_head 0/1