DevQuasar-5/allenai.OLMo-2-1124-13B-Instruct-GGUF

Same weights, converted vs allenai/OLMo-2-1124-13B-Instruct. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, MLP 0/120, Norms 0/161, Attention 0/160, lm_head 0/1

On the Hub · Downloads on Model Pulse