mradermacher/ViGoRL-7b-Spatial-GGUF

Same weights, converted (fewer layers) vs gsarch/ViGoRL-7b-Spatial. mradermacher/ViGoRL-7b-Spatial-GGUF matches part of gsarch/ViGoRL-7b-Spatial (339 of its 729 tensors; the rest of gsarch/ViGoRL-7b-Spatial has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse