nicoboss/DeepSeek-R1-Distill-Qwen-14B-Uncensored
LoRA-style vs deepseek-ai/DeepSeek-R1-Distill-Qwen-14B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Attention 192/336, MLP 144/144, Norms 0/97
7 derivatives checked
- mradermacher/DeepSeek-R1-Distill-Qwen-14B-Uncensored-GGUF: Quantization
- mradermacher/DeepSeek-R1-Distill-Qwen-14B-Uncensored-i1-GGUF: Quantization
- squ0sh/DeepSeek-R1-Distill-Qwen-14B-Uncensored-GGUF: Quantization
- natemiller1928/DeepSeek-R1-Distill-Qwen-14B-Uncensored-Q2_K-GGUF: Quantization
- todayzhxy/DeepSeek-R1-Distill-Qwen-14B-Uncensored-GGUF: Quantization
- fcvcggvvv/DeepSeek-R1-Distill-Qwen-14B-Uncensored-GGUF: Quantization
- nicoboss/DeepSeek-R1-Distill-Qwen-14B-Uncensored-Reasoner: LoRA-style