Update README.md
Browse files
README.md
CHANGED
@@ -5,6 +5,13 @@ license: apache-2.0
|
|
5 |
library_name: transformers
|
6 |
tags:
|
7 |
- python
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
- document
|
9 |
- code
|
10 |
- code2doc
|
@@ -29,17 +36,20 @@ widget:
|
|
29 |
|
30 |
[pip library_etl](https://github.com/PipableAI/pip-library-etl.git)
|
31 |
|
|
|
|
|
32 |
## What have we built?
|
33 |
|
34 |
A 1.3 bn code documentation model that outperforms most models on documenting codes and making your in-house libs ready for LLM and RAG pipelines.
|
35 |
We have also open sourced a [pip library_etl](https://github.com/PipableAI/pip-library-etl.git) for the same, together the lib and model can turn your codebase to functional parse tree ready to be consumed by LLMs to execute complex tasks.
|
36 |
This model is also capable of generating SQL queries with accuracies on par with those of [pip-sql-1.3b](https://huggingface.co/PipableAI/pip-sql-1.3b), with additional capabilities of providing extra examples, instructions ,and column descriptions as context.
|
37 |
-
This is a further trained version of pip-sql-1.3b.
|
|
|
38 |
|
39 |
## How we built it?
|
40 |
|
41 |
We used softmax cross entropy and a modified form of policy grad along with Q loss, optimized in an EM set up.
|
42 |
-
|
43 |
|
44 |
## License
|
45 |
|
|
|
5 |
library_name: transformers
|
6 |
tags:
|
7 |
- python
|
8 |
+
- java
|
9 |
+
- cpp
|
10 |
+
- sql
|
11 |
+
- function calling
|
12 |
+
- unit tests
|
13 |
+
- causalLM
|
14 |
+
- codeLLAMA modified archi
|
15 |
- document
|
16 |
- code
|
17 |
- code2doc
|
|
|
36 |
|
37 |
[pip library_etl](https://github.com/PipableAI/pip-library-etl.git)
|
38 |
|
39 |
+
[linkedin_post](https://www.linkedin.com/posts/pipable%2Eai_github-pipableaipip-library-etl-this-activity-7179111129678327809-Pgxy?utm_source=share&utm_medium=member_desktop)
|
40 |
+
|
41 |
## What have we built?
|
42 |
|
43 |
A 1.3 bn code documentation model that outperforms most models on documenting codes and making your in-house libs ready for LLM and RAG pipelines.
|
44 |
We have also open sourced a [pip library_etl](https://github.com/PipableAI/pip-library-etl.git) for the same, together the lib and model can turn your codebase to functional parse tree ready to be consumed by LLMs to execute complex tasks.
|
45 |
This model is also capable of generating SQL queries with accuracies on par with those of [pip-sql-1.3b](https://huggingface.co/PipableAI/pip-sql-1.3b), with additional capabilities of providing extra examples, instructions ,and column descriptions as context.
|
46 |
+
This is a further trained version of pip-sql-1.3b and performance comparable to GPT.
|
47 |
+
|
48 |
|
49 |
## How we built it?
|
50 |
|
51 |
We used softmax cross entropy and a modified form of policy grad along with Q loss, optimized in an EM set up.
|
52 |
+
The performance for the metioned tasks are comparable to much bigger LLMs and GPT-3.5
|
53 |
|
54 |
## License
|
55 |
|