ArRENCEAI/DeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED

Partial fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B. Partial change: 26% of the weights changed (attention, lm_head, mlp), in 5 of 28 layers.

Tensors changed: Embeddings 0/1, Attention 25/196, MLP 15/84, Norms 0/57, lm_head 1/1

2 derivatives checked

• mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED-i1-GGUF: Quantization
• mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse