mradermacher/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small-GGUF

Same weights, converted vs ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1

On the Hub · Downloads on Model Pulse