HelpingAI/HELVETE
LoRA-style vs HelpingAI/HelpingAI2-6B. 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 22 of 22 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/45, MLP 66/66, Attention 88/88, lm_head 0/1
5 derivatives checked
- mradermacher/NSFW-6B-i1-GGUF: Quantization
- mradermacher/NSFW-6B-GGUF: Quantization
- mradermacher/HELVETE-i1-GGUF: Quantization
- mradermacher/HELVETE-GGUF: Same weights, converted
- raethehacker/NSFW-6B-Q2_K-GGUF: Quantization