InferenceIllusionist/Excalibur-7b-DPO
LoRA-style vs InferenceIllusionist/Excalibur-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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 0/1
6 derivatives checked
- mradermacher/Excalibur-7b-DPO-i1-GGUF: Quantization
- featherless-ai-quants/InferenceIllusionist-Excalibur-7b-DPO-GGUF: Quantization
- InferenceIllusionist/Excalibur-7b-DPO-GGUF: Quantization
- InferenceIllusionist/Excalibur-7b-DPO-iMat-GGUF: Quantization
- giannisan/Jett-w26-abliterated: Full fine-tune
- JDBMG/Hapsburg_v0_1: Full fine-tune