DevQuasar/nvidia.Cosmos-Reason1-7B-GGUF

Full fine-tune (fewer layers) vs nvidia/Cosmos-Reason1-7B. DevQuasar/nvidia.Cosmos-Reason1-7B-GGUF matches part of nvidia/Cosmos-Reason1-7B (339 of its 729 tensors; the rest of nvidia/Cosmos-Reason1-7B has no counterpart). On the shared part: DevQuasar/nvidia.Cosmos-Reason1-7B-GGUF is a GGUF (F16) of different weights. Fine-tune: 93% of the weights changed, across 28 of 28 layers.

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

On the Hub · Downloads on Model Pulse