mradermacher/SindhiLLM-1B-v0.1-GGUF
Same weights, converted vs jamalimubashirali/SindhiLLM-1B-v0.1. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64
Same weights, converted vs jamalimubashirali/SindhiLLM-1B-v0.1. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64