mradermacher/SJTPass-4-GGUF

Same weights, converted vs Sakalti/SJTPass-4. Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/121, MLP 0/180, Attention 0/420

On the Hub · Downloads on Model Pulse