DevQuasar-10/bigscience.bloom-GGUF

Quantization vs bigscience/bloom. DevQuasar-10/bigscience.bloom-GGUF is a GGUF quantization (Q8_0) of the same weights: 494 tensors match exactly and 211 within quantization error.

Tensors changed: Embeddings 0/3, Norms 0/282, MLP 0/280, Attention 0/140

On the Hub · Downloads on Model Pulse