lmstudio-community/Jedi-7B-1080p-GGUF

Quantization (fewer layers) vs xlangai/Jedi-7B-1080p. lmstudio-community/Jedi-7B-1080p-GGUF matches part of xlangai/Jedi-7B-1080p (339 of its 729 tensors; the rest of xlangai/Jedi-7B-1080p has no counterpart). On the shared part: lmstudio-community/Jedi-7B-1080p-GGUF is a GGUF quantization (Q8_0) of the same weights: 141 tensors match exactly and 198 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1

On the Hub · Downloads on Model Pulse