decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP
LoRA-style vs mlabonne/Marcoro14-7B-slerp. 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
7 derivatives checked
- mradermacher/kellemar-DPO-Orca-Distilled-7B-SLERP-i1-GGUF: Quantization
- mradermacher/kellemar-DPO-Orca-Distilled-7B-SLERP-GGUF: Same weights, converted
- jsfs11/WestOrcaNeuralMarco-DPO-v2-DARETIES-7B-GGUF: Full fine-tune
- jsfs11/WestOrcaNeuralMarco-DPO-v2-DARETIES-7B: Full fine-tune
- liminerity/Blur-7b-v1.21: Full fine-tune
- jsfs11/WestOrcaDPO-7B-GTA: Full fine-tune
- laislemke/turdus-orca-slerp: LoRA-style