DopeyGay/L3-DeepDolph-R1-8B
Partial fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Llama-8B. Partial change: 81% of the weights changed (attention, mlp, norms), in 30 of 32 layers.
Tensors changed: Embeddings 0/1, Attention 120/128, MLP 90/96, Norms 60/65, lm_head 0/1
4 derivatives checked
- mradermacher/L3-DeepDolph-R1-8B-i1-GGUF: Quantization
- mradermacher/L3-DeepDolph-R1-8B-GGUF: Same weights, converted
- DopeyGay/L3-DeepDolph-Stheria-8B: Full fine-tune
- DopeyGay/L3-UnholyDolph-R1-8B: Partial fine-tune