mradermacher/Llama3.1-8B-Reasoner-v0_3-GGUF

Same weights, converted vs wzebrowski/Llama3.1-8B-Reasoner-v0_3. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse