nicoboss/DeepSeek-R1-Distill-Qwen-7B-Uncensored
LoRA-style vs deepseek-ai/DeepSeek-R1-Distill-Qwen-7B. 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 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Attention 112/196, MLP 84/84, Norms 0/57
3 derivatives checked
- mradermacher/DeepSeek-R1-Distill-Qwen-7B-Uncensored-i1-GGUF: Quantization
- mradermacher/DeepSeek-R1-Distill-Qwen-7B-Uncensored-GGUF: Same weights, converted
- nicoboss/DeepSeek-R1-Distill-Qwen-7B-Uncensored-Reasoner: LoRA-style