bartowski/jtl11_GLM-4.7-Flash-heretic-GGUF

Same weights, converted vs jtl11/GLM-4.7-Flash-heretic. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 278 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/189, MLP 0/187, Attention 0/188

On the Hub · Downloads on Model Pulse