mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-GGUF

Same weights, converted vs MasterControlAIML/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196

On the Hub · Downloads on Model Pulse