AtomicChat posts uncensored Inkling-2-Mini GGUF builds
AtomicChat says its adapter drops refusal to zero on its harmful tests while missing its MMLU and first-token KL gates.
36
AtomicChat says its adapter drops refusal to zero on its harmful tests while missing its MMLU and first-token KL gates.
AtomicChat releases 763B DeepSeek-V4.1-Flash-1017 uncensored GGUF quantized for single 12GB GPU with Strata.
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.
Today 1.1K readers · 1.3K views · 129 reads · all time 215K views