mradermacher/openPangu-Embedded-1B-GGUF
Same weights, converted vs FreedomIntelligence/openPangu-Embedded-1B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/208
Same weights, converted vs FreedomIntelligence/openPangu-Embedded-1B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/208