Model Merging Quiz

Answers and explanations appear as you take the quiz.

1. What does model merging primarily combine?
   • The weights (parameters) of multiple models
   • The training datasets of multiple models
   • The output predictions of multiple models at inference time
   • The hardware accelerators used for training
2. A 'task vector' is best described as:
   • The list of tasks a model can perform
   • The difference between a fine-tuned model's weights and its base model's weights
   • A vector of input tokens for a task
   • The gradient computed during a single training step
3. In the described weight-space merging methods, what can be avoided?
   • Evaluation of the merged checkpoint
   • Compatibility requirements between model weights
   • Additional gradient training and access to the original training data
   • Testing the result on intended tasks
4. How do TIES-Merging and DARE differ in addressing parameter interference?
   • Both use the same sign-voting method and differ only in scale
   • DARE uses prompt engineering while TIES retrains on joint data
   • Both average model outputs instead of changing weights
   • They use different techniques: TIES resolves sign conflicts, while DARE drops and rescales task-vector entries
5. A key precondition for two models to be merged successfully is that they:
   • Share the same architecture and typically descend from a common base model
   • Were trained on identical data
   • Have exactly the same number of training steps
   • Use the same tokenizer vocabulary size only
6. In task arithmetic, what do coefficients control when combining task vectors?
   • Which tokenizer each checkpoint must use
   • How strongly each parameter-change vector contributes to the merged checkpoint
   • How many training examples are generated
   • Whether an evaluation set is required
7. What are the three main stages named by TIES-Merging?
   • Tokenize text, infer emotions, and export audio
   • Quantize weights, shard GPUs, and route network packets
   • Trim small changes, elect a sign direction, then merge aligned parameter updates
   • Train a reward model, collect labels, and run PPO
8. Why should teams evaluate each task after a model merge?
   • Merging guarantees every benchmark improves
   • Evaluation is needed only to calculate the file size
   • A merged model cannot be run without retraining
   • Combining weight updates can create interference or reduce performance on a task