ykarout/RPT-DeepSeek-R1-0528-Qwen3-8B
Partial fine-tune vs deepseek-ai/DeepSeek-R1-0528-Qwen3-8B. Partial change: 85% of the weights changed (attention, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 0/1, Attention 144/144, Norms 81/145, MLP 108/108, lm_head 0/1
2 derivatives checked
- mradermacher/RPT-DeepSeek-R1-0528-Qwen3-8B-i1-GGUF: Quantization
- mradermacher/RPT-DeepSeek-R1-0528-Qwen3-8B-GGUF: Same weights, converted