mradermacher/HelpingAI-flash-GGUF
Same weights, converted vs OEvortex/HelpingAI-flash. Same weights stored in another dtype (F32/F16 → F16/F32).
Tensors changed: MLP 0/75, Attention 0/100, Embeddings 0/1, Norms 0/102, lm_head 0/1
Same weights, converted vs OEvortex/HelpingAI-flash. Same weights stored in another dtype (F32/F16 → F16/F32).
Tensors changed: MLP 0/75, Attention 0/100, Embeddings 0/1, Norms 0/102, lm_head 0/1