mradermacher/gpt-oss-nano-GGUF
Same weights, converted vs squ11z1/gpt-oss-nano. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 168 new tensors.
Tensors changed: Norms 0/49, lm_head 0/1, Embeddings 0/1, MLP 0/48, Attention 0/192
Same weights, converted vs squ11z1/gpt-oss-nano. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 168 new tensors.
Tensors changed: Norms 0/49, lm_head 0/1, Embeddings 0/1, MLP 0/48, Attention 0/192