mradermacher/sea-lion-7b-instruct-research-GGUF
Same weights, converted vs aisingapore/SEA-LION-v1-7B-IT-Research. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Attention 0/256, MLP 0/128, Norms 0/130, Embeddings 0/2
Same weights, converted vs aisingapore/SEA-LION-v1-7B-IT-Research. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Attention 0/256, MLP 0/128, Norms 0/130, Embeddings 0/2