mradermacher/pythia-2.8b-thai-base-v1-GGUF
Same weights, converted vs Naphon/pythia-2.8b-thai-base-v1. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/2, Attention 0/64, Norms 0/130, MLP 0/128
Same weights, converted vs Naphon/pythia-2.8b-thai-base-v1. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/2, Attention 0/64, Norms 0/130, MLP 0/128