Update README.md
Browse files
README.md
CHANGED
|
@@ -28,7 +28,7 @@ prior to senior year in order to build a new project or continue a previous one.
|
|
| 28 |
|
| 29 |
|
| 30 |
|
| 31 |
-
Technical Approach:
|
| 32 |
|
| 33 |
-Multi-task Training: Curated custom dataset batches across various administrative capabilities such as tool calling, summarization and RAG
|
| 34 |
|
|
@@ -40,7 +40,7 @@ Technical Approach:
|
|
| 40 |
|
| 41 |
|
| 42 |
|
| 43 |
-
Some Challenges:
|
| 44 |
|
| 45 |
|
| 46 |
-The very first training run I forgot I was working with a dictionary and accidentally assigned the variables wrong so every model was trained on "question"-"answer" repeatedly
|
|
@@ -56,7 +56,7 @@ Technical Approach:
|
|
| 56 |
|
| 57 |
|
| 58 |
|
| 59 |
-
Model Rationale
|
| 60 |
|
| 61 |
-I was originally going to try Mistral Small 3 24B but it was too large and expensive
|
| 62 |
|
|
@@ -71,7 +71,7 @@ Technical Approach:
|
|
| 71 |
|
| 72 |
|
| 73 |
|
| 74 |
-
Current Goal?
|
| 75 |
|
| 76 |
-My current goal this senior year is phase 2 of the project, working on a custom agent, built on the smolagents framework, for this model to use in day to day life
|
| 77 |
|
|
|
|
| 28 |
|
| 29 |
|
| 30 |
|
| 31 |
+
# Technical Approach:
|
| 32 |
|
| 33 |
-Multi-task Training: Curated custom dataset batches across various administrative capabilities such as tool calling, summarization and RAG
|
| 34 |
|
|
|
|
| 40 |
|
| 41 |
|
| 42 |
|
| 43 |
+
# Some Challenges:
|
| 44 |
|
| 45 |
|
| 46 |
-The very first training run I forgot I was working with a dictionary and accidentally assigned the variables wrong so every model was trained on "question"-"answer" repeatedly
|
|
|
|
| 56 |
|
| 57 |
|
| 58 |
|
| 59 |
+
# Model Rationale
|
| 60 |
|
| 61 |
-I was originally going to try Mistral Small 3 24B but it was too large and expensive
|
| 62 |
|
|
|
|
| 71 |
|
| 72 |
|
| 73 |
|
| 74 |
+
# Current Goal?
|
| 75 |
|
| 76 |
-My current goal this senior year is phase 2 of the project, working on a custom agent, built on the smolagents framework, for this model to use in day to day life
|
| 77 |
|