DevQuasar/ByteDance-Seed.cudaLLM-8B-GGUF
Same weights, converted vs ByteDance-Seed/cudaLLM-8B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1
Same weights, converted vs ByteDance-Seed/cudaLLM-8B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1