analyzing 35 models temperature: 0 num_ctx: 2048 prompt: updating model: llama2-uncensored:latest pulling manifest pulling 6aa74acf170f pulling 8c17c2ebb0ea pulling 7c23fb36d801 pulling 28577ba2177f pulling 0025f348941e pulling c67e365e770d verifying sha256 digest writing manifest removing any unused layers success loading model: llama2-uncensored:latest size: 3649M par: 7B fam: llama parameter_size: 7B quantization_level: Q4_0 template: parameters: random check: 00 AC 88 B1 CB 1E 72 C1 79 75