Update README.md
Browse files
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
|
|
|
|
| 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
|