Commit
•
5da8127
1
Parent(s):
1ac317b
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- bigcode/the-stack
|
4 |
+
---
|
5 |
+
# hexcoder 3b (replit)
|
6 |
+
|
7 |
+
![hex_stickers](https://www.mitchelloharawild.com/blog/2018-07-10-hexwall_files/figure-html/final-1.png)
|
8 |
+
|
9 |
+
This is a model that trains the base [replit code model](https://huggingface.co/replit/replit-code-v1-3b) on R coding instructions, which are brief questions to which I have formulated a brief anwser.
|
10 |
+
|
11 |
+
Then I intend to instruction tune the model on all stackoverflow questions and anwsers with the tag 'r' in the 2011 to 2016 timeframe, presenting stackoverflow questions as <|user|> and the best answer as <|assistant|>. This will teach the model that it is expected to produce an answer to a user's question about 'r'.
|
12 |
+
|
13 |
+
The intended outcome is a reasonably adequate model which can answer basic r user questions, but more broadly an evaluaion of the data/sources and training needed to produce great open source code generating models for r.
|