CorticalStack/pastiche-crown-clown-7b-dare-dpo
LoRA-style vs CorticalStack/pastiche-crown-clown-7b-dare. 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: MLP 96/96, Attention 128/128, Norms 0/65, Embeddings 0/1, lm_head 0/1
9 derivatives checked
- featherless-ai-quants/CorticalStack-pastiche-crown-clown-7b-dare-dpo-GGUF: Quantization
- mradermacher/pastiche-crown-clown-7b-dare-dpo-i1-GGUF: Quantization
- arcee-ai/Clown-DPO-Extended: Partial fine-tune
- automerger/Experiment27Pastiche-7B: Full fine-tune
- Kukedlc/Neural-4-QA-7b: Full fine-tune
- automerger/PasticheAlloyingotneoy-7B: Full fine-tune
- automerger/Experiment26Pastiche-7B: Full fine-tune
- mayacinka/yam-pastiche-7B-franken: Full fine-tune
- jambroz/FNCARL-7b: Full fine-tune