Fresher / New Grad

FP4 vs NF4, pick the answer that captures the actual structural difference

Why does dropping the EOS token from SFT labels produce a model that never stops generating?

Name the signal early stopping watches, and explain the 'patience' knob

Explain what gets quantized the second time in QLoRA's double-quantization step

Fill in the DeepSpeed config keys that select a ZeRO stage

Which of these is actually saved when a fine-tuning checkpoint is written?

Define the role of a chat template when fine-tuning on (system, user, assistant) data

What does bnb_4bit_compute_dtype actually control in a QLoRA config?

bf16 vs fp16: which one preserves fp32's exponent range?

Micro batch vs effective batch in fine-tuning: give the relationship

Base model vs instruction-tuned model: what does the user actually feel?

lora_alpha in plain English: what role does that scalar play?

Alpaca-format examples carry three fields: name them

Adam optimizer state per parameter: fill in the moment buffers and bytes

Accelerate launch: what does that one CLI actually wire up?

Compute the LoRA trainable param count for a 4096x4096 projection at rank r=8

Fill in the memory delta when a 7B weight tensor moves from fp32 to bf16

At which step in the attention pipeline does the mask actually take effect?

Why split V from K instead of just reusing K as the value vector?

Each row of the post-softmax attention weight matrix corresponds to which side of the QK product?

Pick what happens to attention weights when pre-softmax scores are divided by a temperature T > 1

Along which axis of the QK^T score matrix is softmax applied inside attention?

Name the two properties softmax guarantees for every row of the attention weight matrix

Which token most often serves as an attention sink in pretrained autoregressive LLMs?

How does softmax turn an attention score into an attention weight?