Update README.md
Browse files
README.md
CHANGED
@@ -12,20 +12,29 @@ language:
|
|
12 |
datasets:
|
13 |
- openai/gsm8k
|
14 |
---
|
15 |
-
This is my first reasoning model. It is fairly small and yes it still gets the answer wrong to how many r's in the word strawberry.
|
16 |
|
17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
-
In your system prompt use:
|
20 |
Respond in the following format:
|
|
|
|
|
21 |
<reasoning>
|
22 |
...
|
23 |
</reasoning>
|
24 |
<answer>
|
25 |
...
|
26 |
</answer>
|
|
|
|
|
|
|
27 |
|
28 |
-
|
29 |
|
30 |
Enjoy, but please note that this model is experimental and I used it to define my pipeline.
|
31 |
|
|
|
12 |
datasets:
|
13 |
- openai/gsm8k
|
14 |
---
|
|
|
15 |
|
16 |
+
# My Reasoning Model
|
17 |
+
|
18 |
+
This is my first reasoning model. It is fairly small, and yes, it still gets the answer wrong to how many r's are in the word "strawberry."
|
19 |
+
|
20 |
+
You are welcome to use the model as you wish.
|
21 |
+
|
22 |
+
## System Prompt Format
|
23 |
|
|
|
24 |
Respond in the following format:
|
25 |
+
|
26 |
+
```
|
27 |
<reasoning>
|
28 |
...
|
29 |
</reasoning>
|
30 |
<answer>
|
31 |
...
|
32 |
</answer>
|
33 |
+
```
|
34 |
+
|
35 |
+
I fine-tuned the model using `openai/gsm8k`, and to ensure costs do not go insane, I used a single A100.
|
36 |
|
37 |
+
```
|
38 |
|
39 |
Enjoy, but please note that this model is experimental and I used it to define my pipeline.
|
40 |
|