mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF

Same weights, converted vs jukofyork/DeepSeek-R1-DRAFT-0.6B-v3.0. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168

On the Hub · Downloads on Model Pulse