gemma 2 2b it abliterated

Gemma 2

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released July 20248K context≈ 6,144 words2b params

A compact, uncensored variant of Google's Gemma 2 2B, modified by IlyaGusev through an abliteration process that removes refusal behaviors. It responds more freely to a wider range of prompts than the base instruction-tuned model, though as a 2B parameter model it carries the expected limitations in reasoning depth and factual reliability that come with smaller architectures.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Factual Knowledge

Moderate

Tool Use

gemma 2 2b it abliterated

Gemma 2

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released July 20248K context≈ 6,144 words2b params

A compact, uncensored variant of Google's Gemma 2 2B, modified by IlyaGusev through an abliteration process that removes refusal behaviors. It responds more freely to a wider range of prompts than the base instruction-tuned model, though as a 2B parameter model it carries the expected limitations in reasoning depth and factual reliability that come with smaller architectures.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Factual Knowledge

Moderate

Tool Use

Glossary

AbliterationA technique that removes or disables a model's built-in safety refusal mechanisms, allowing it to respond to a wider range of requests.Instruction-TunedA model fine-tuned on instruction-response pairs so it follows user prompts more reliably.Parameter ModelA neural network described by the number of learnable weights it contains; more parameters generally mean greater capacity to learn complex patterns, but also require more computational resources.ReasoningThe model's ability to work through multi-step logical problems and provide justified answers rather than just pattern-matching.Reasoning DepthA model's ability to perform complex multi-step logical thinking and problem-solving; typically increases with model size.UncensoredA model without built-in safety filters or content restrictions, allowing it to generate responses on any topic without refusal.

Capabilities

Capabilities

Use Case Fit

Glossary