knifeayumu/Negative-Anubis-70B-v1
LoRA-style vs SicariusSicariiStuff/Negative_LLAMA_70B. 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 80 of 80 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 240/240, Attention 320/320, lm_head 0/1
3 derivatives checked
- bartowski/Negative-Anubis-70B-v1-GGUF: Quantization
- mradermacher/Negative-Anubis-70B-v1-i1-GGUF: Quantization
- mradermacher/Negative-Anubis-70B-v1-GGUF: Quantization