mradermacher/walnoot-8b-instruct-GGUF

Same weights, converted vs WAINUT/walnoot-8b-instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/129, MLP 0/64, Attention 0/128

On the Hub · Downloads on Model Pulse