mradermacher/LD-Zephyria-37b-GGUF

Quantization vs SteelStorage/LD-Zephyria-37b. mradermacher/LD-Zephyria-37b-GGUF is a GGUF quantization (Q8_0) of the same weights: 191 tensors match exactly and 667 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/191, MLP 0/285, Attention 0/380

On the Hub · Downloads on Model Pulse