suayptalha
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -1,7 +1,31 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
tags:
|
4 |
-
- unsloth
|
5 |
-
- trl
|
6 |
-
- sft
|
7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- unsloth
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- text-generation-inference
|
8 |
+
datasets:
|
9 |
+
- jeggers/competition_math
|
10 |
+
language:
|
11 |
+
- en
|
12 |
+
base_model:
|
13 |
+
- meta-llama/Llama-3.2-3B-Instruct
|
14 |
+
pipeline_tag: text-generation
|
15 |
+
library_name: transformers
|
16 |
+
---
|
17 |
+
|
18 |
+
![Komodo-Logo](Komodo-Logo.jpg)
|
19 |
+
|
20 |
+
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.
|
21 |
+
|
22 |
+
This model is fp16. You should import it using torch_dtype="float16".
|
23 |
+
|
24 |
+
Finetune system prompt:
|
25 |
+
```
|
26 |
+
You are a highly intelligent and accurate mathematical assistant.
|
27 |
+
You will solve mathematical problems step by step, explain your reasoning clearly, and provide concise, correct answers.
|
28 |
+
When the solution requires multiple steps, detail each step systematically.
|
29 |
+
```
|
30 |
+
|
31 |
+
You can use ChatML format!
|