hyper-accel
/

ci-2layer-llama2-7b

Model card Files Files and versions

ci-2layer-llama2-7b / tokenizer.json

ELutris's picture

KD-distilled 2-layer student against Llama-2-7B teacher (alpaca-cleaned, 1500 steps, T=2.0, KL loss)

f0597fe verified 3 days ago

history contribute delete

3.62 MB

File too large to display, you can check the raw version instead.