Commit
•
5345544
1
Parent(s):
d857b0e
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,4 +10,19 @@ tags:
|
|
| 10 |
- unsloth
|
| 11 |
datasets:
|
| 12 |
- jeggers/competition_math
|
| 13 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
- unsloth
|
| 11 |
datasets:
|
| 12 |
- jeggers/competition_math
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
This version of Komodo is a Llama-3.2-3B-Instruct finetuned model on jeggers/competition_math dataset to increase math performance of the base model.
|
| 19 |
+
|
| 20 |
+
This model is 4bit-quantizated. You should import it 8bit if you want to use 3B parameters!
|
| 21 |
+
Make sure you installed 'bitsandbytes' library before import.
|
| 22 |
+
|
| 23 |
+
Finetune system prompt:
|
| 24 |
+
You are a highly intelligent and accurate mathematical assistant.
|
| 25 |
+
You will solve mathematical problems step by step, explain your reasoning clearly, and provide concise, correct answers.
|
| 26 |
+
When the solution requires multiple steps, detail each step systematically.
|
| 27 |
+
|
| 28 |
+
You can use ChatML format!
|