Update README.md
Browse files
README.md
CHANGED
@@ -11,11 +11,11 @@ datasets:
|
|
11 |
|
12 |
---
|
13 |
|
14 |
-
# GPT-Code-Clippy-
|
15 |
|
16 |
## Model Description
|
17 |
|
18 |
-
GPT-CC-
|
19 |
|
20 |
## Training data
|
21 |
|
@@ -58,7 +58,7 @@ python run_clm_apps.py \
|
|
58 |
|
59 |
## Intended Use and Limitations
|
60 |
|
61 |
-
The model is
|
62 |
|
63 |
### How to use
|
64 |
|
@@ -104,11 +104,9 @@ The paper ["Evaluating Large Language Models Trained on Code"](https://arxiv.org
|
|
104 |
|
105 |
2. **Economic and labor market impacts:** Large language models trained on large code datasets such as this one that are capable of generating high-quality code have the potential to automate part of the software development process. This may negatively impact software developers. However, as discussed in the paper, as shown in the Summary Report of software developers from [O*NET OnLine](https://www.onetonline.org/link/summary/15-1252.00), developers don't just write software.
|
106 |
|
107 |
-
5. **Biases:** The model is trained on data containing prompt questions formatted in specific way. The performance of the model can be worse if the prompt
|
108 |
|
109 |
-
|
110 |
-
|
111 |
-
GPT-CC is finetuned GPT-Neo and might have inhereted biases and limitations from it. See [GPT-Neo model card](https://huggingface.co/EleutherAI/gpt-neo-125M#limitations-and-biases) for details.
|
112 |
|
113 |
## Eval results
|
114 |
|
|
|
11 |
|
12 |
---
|
13 |
|
14 |
+
# GPT-Code-Clippy-1.3B-APPS-all
|
15 |
|
16 |
## Model Description
|
17 |
|
18 |
+
GPT-CC-1.3B-APPS-all is a GPT-Neo-1.3B fine-tuned on APPS dataset. This model is specialized to solve programming tasks.
|
19 |
|
20 |
## Training data
|
21 |
|
|
|
58 |
|
59 |
## Intended Use and Limitations
|
60 |
|
61 |
+
The model is fine-tuned to solve programming problems given a text description and optional starter code.
|
62 |
|
63 |
### How to use
|
64 |
|
|
|
104 |
|
105 |
2. **Economic and labor market impacts:** Large language models trained on large code datasets such as this one that are capable of generating high-quality code have the potential to automate part of the software development process. This may negatively impact software developers. However, as discussed in the paper, as shown in the Summary Report of software developers from [O*NET OnLine](https://www.onetonline.org/link/summary/15-1252.00), developers don't just write software.
|
106 |
|
107 |
+
5. **Biases:** The model is trained on data containing prompt questions formatted in specific way. The performance of the model can be worse if the prompt formatting is different from that used in APPS dataset.
|
108 |
|
109 |
+
This model is finetuned GPT-Neo and might have inhereted biases and limitations from it. See [GPT-Neo model card](https://huggingface.co/EleutherAI/gpt-neo-125M#limitations-and-biases) for details.
|
|
|
|
|
110 |
|
111 |
## Eval results
|
112 |
|