DevQuasar/inclusionAI.Ling-1T-GGUF

Quantization vs inclusionAI/Ling-1T. DevQuasar/inclusionAI.Ling-1T-GGUF is a GGUF quantization (Q8_0) of the same weights: 397 tensors match exactly and 322 within quantization error.

Tensors changed: Embeddings 0/1, Attention 0/80, MLP 0/316, Norms 0/321, lm_head 0/1

On the Hub · Downloads on Model Pulse