cafierom commited on
Commit
ce51914
·
verified ·
1 Parent(s): cbead1b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -3
README.md CHANGED
@@ -9,15 +9,16 @@ python_version: '3.12'
9
  app_file: app.py
10
  pinned: false
11
  license: mit
12
- short_description: Finds inflection points in model outputs and displays diffs
 
13
  ---
14
 
15
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
16
-
17
  # InflectionLM: Output and Token Visualization
18
 
19
  InflectionLM is a tool designed to visualize "inflection points" in Large Language Model (LLM) generation. By leveraging independent sampling, the tool generates multiple alternative output paths and identifies tokens where the model's confidence was low, highlighting these as potential points where the generation could have diverged.
20
 
 
 
21
  ## 🌟 Features
22
 
23
  - **Diverse Response Generation**: Generates 3 independent responses for every prompt using the GEMMA 4 model, utilizing Top-P (Nucleus) and Top-K sampling to maximize diversity.
@@ -84,3 +85,6 @@ The tool uses **Multinomial Sampling** with Top-P and Top-K filtering to generat
84
 
85
  Tokens with a probability $< 0.6$ are considered "unconfident." In linguistic terms, these are the "inflections"—moments where the model's internal probability distribution was flatter, meaning alternative tokens were almost as likely, leading to potential variations in the final text.
86
 
 
 
 
 
9
  app_file: app.py
10
  pinned: false
11
  license: mit
12
+ short_description: Finds inflection points in model outputs and displays scores
13
+ tracks: Backyard AI
14
  ---
15
 
 
 
16
  # InflectionLM: Output and Token Visualization
17
 
18
  InflectionLM is a tool designed to visualize "inflection points" in Large Language Model (LLM) generation. By leveraging independent sampling, the tool generates multiple alternative output paths and identifies tokens where the model's confidence was low, highlighting these as potential points where the generation could have diverged.
19
 
20
+ [Watch a video demo on LinkedIn!](https://www.linkedin.com/posts/mauricio-cafiero-5481259b_buildsmallhackathon-gemma4-huggingface-ugcPost-7472245848584683521-L4hx)
21
+
22
  ## 🌟 Features
23
 
24
  - **Diverse Response Generation**: Generates 3 independent responses for every prompt using the GEMMA 4 model, utilizing Top-P (Nucleus) and Top-K sampling to maximize diversity.
 
85
 
86
  Tokens with a probability $< 0.6$ are considered "unconfident." In linguistic terms, these are the "inflections"—moments where the model's internal probability distribution was flatter, meaning alternative tokens were almost as likely, leading to potential variations in the final text.
87
 
88
+ --
89
+
90
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference