mradermacher/Ocelot-Ko-self-instruction-10.8B-v1.0-GGUF

Same weights, converted vs cpm-ai/Ocelot-Ko-self-instruction-10.8B-v1.0. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/192, lm_head 0/1

On the Hub · Downloads on Model Pulse