Skip to content

Update 8.mdx #1206

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
syedmuhammadayyanibrar wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update 8.mdx #1206

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions chapters/en/chapter1/8.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,8 +119,8 @@ One common challenge with LLMs is their tendency to repeat themselves - much lik

![image](https://huggingface.co/reasoning-course/images/resolve/main/inference/2.png)

These penalties are applied early in the token selection process, adjusting the raw probabilities before other sampling strategies are applied. Think of them as gentle nudges encouraging the model to explore new vocabulary.

These penalties are applied early in the token selection process, adjusting the raw probabilities before other sampling strategies are applied. Think of them as gentle nudges encouraging the model to explore new vocabulary.
``` LOGIT GENERATION --> PENALTY ADJUSTMENT --> SOFTMAX CALCULATION --> SAMPLING (Temperature/Top-P) --> SAMPLING (Temperature/Top-P)```
### Controlling Generation Length: Setting Boundaries

Just as a good story needs proper pacing and length, we need ways to control how much text our LLM generates. This is crucial for practical applications - whether we're generating a tweet-length response or a full blog post.
Expand Down