lkevincc0/Step-3.5-Flash-REAP-128B-A11B
Same weights, repacked vs stepfun-ai/Step-3.5-Flash. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/188, MLP 0/138, Attention 0/230, lm_head 0/1, other 0/2
2 derivatives checked
- mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF: Quantization
- mradermacher/Step-3.5-Flash-REAP-128B-A11B-GGUF: Quantization