mradermacher/OLMo-2-1B-7x-GGUF

Same weights, converted vs sbordt/OLMo-2-1B. Same weights stored in another dtype (F32 → F16/F32).

Tensors changed: Embeddings 0/1, MLP 0/48, Norms 0/65, Attention 0/64, lm_head 0/1

On the Hub · Downloads on Model Pulse