mradermacher/Mini-Lama-8B-Base-GGUF

Same weights, converted vs Nabbers1999/Mini-Llama-8B-Base-0124. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Norms 0/69, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse