nicoboss/DeepSeek-V2-Lite-Chat-Uncensored
LoRA-style vs deepseek-ai/DeepSeek-V2-Lite-Chat. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, kv_a_proj_with_mqa, kv_b_proj, o_proj, q_proj, up_proj changed, in 27 of 27 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/82, MLP 2782/2808, Attention 108/108
3 derivatives checked
- mradermacher/DeepSeek-V2-Lite-Chat-Uncensored-i1-GGUF: Quantization
- mradermacher/DeepSeek-V2-Lite-Chat-Uncensored-GGUF: Quantization
- nicoboss/DeepSeek-V2-Lite-Chat-Uncensored-Unbiased: LoRA-style