Gemma3 family is out! Reading the tech report, and this section was really interesting to me from a methods/scientific fairness pov.
Instead of doing over-hyped comparisons, they clearly state that **results are reported in a setup which is advantageous to their models**. (Which everybody does, but people usually don't say)
For a tech report, it makes a lot of sense to report model performance when used optimally! On leaderboards on the other hand, comparison will be apples to apples, but in a potentially unoptimal way for a given model family (like some user interact sub-optimally with models)
Also contains a cool section (6) on training data memorization rate too! Important to see if your model will output the training data it has seen as such: always an issue for privacy/copyright/... but also very much for evaluation!
Because if your model knows its evals by heart, you're not testing for generalization.
Detect hallucinations in answers based on context and questions using ModernBERT with 8192-token context support!
### Model Details - **Model Name**: [lettucedect-large-modernbert-en-v1](KRLabsOrg/lettucedect-large-modernbert-en-v1) - **Organization**: [KRLabsOrg](https://huggingface.co/KRLabsOrg) - **Github**: [https://github.com/KRLabsOrg/LettuceDetect](https://github.com/KRLabsOrg/LettuceDetect) - **Architecture**: ModernBERT (Large) with extended context support up to 8192 tokens - **Task**: Token Classification / Hallucination Detection - **Training Dataset**: [RagTruth](wandb/RAGTruth-processed) - **Language**: English - **Capabilities**: Detects hallucinated spans in answers, provides confidence scores, and calculates average confidence across detected spans.
LettuceDetect excels at processing long documents to determine if an answer aligns with the provided context, making it a powerful tool for ensuring factual accuracy.
Check out [DeepSeek-R1 INT2 model(OPEA/DeepSeek-R1-int2-mixed-sym-inc). This 200GB DeepSeek-R1 model shows only about a 2% drop in MMLU, though it's quite slow due to kernel issue.