analyzing 36 models temperature: 0.4 num_ctx: 2048 prompt: updating model: unclemusclez/wizardlm2-7b-abliterated:latest pulling manifest pulling 3664f0c3d415 pulling 181a5fe91ed8 verifying sha256 digest writing manifest removing any unused layers success loading model: unclemusclez/wizardlm2-7b-abliterated:latest size: 4166M par: 7.2B fam: llama parameter_size: 7.2B quantization_level: Q4_K_M template: parameters: