mradermacher/Fabliq-8B-Agent-FromBase-Reasoning-GGUF

Same weights, converted vs LLM-OS-Models/Fabliq-8B-Agent-FromBase-Reasoning. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 88 new tensors.

Tensors changed: Embeddings 0/2, other 0/36, MLP 0/28, Norms 0/60, Attention 0/24

On the Hub · Downloads on Model Pulse