a103e3e9e2
This PR adds a tutorial to self distill and train medusa heads for a specific model --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com> |
||
---|---|---|
.. | ||
flash_attention.md | ||
guidance.md | ||
paged_attention.md | ||
quantization.md | ||
safetensors.md | ||
speculation.md | ||
streaming.md | ||
tensor_parallelism.md |