Update README.md
Browse files
README.md
CHANGED
@@ -18,12 +18,6 @@ This repository contains:
|
|
18 |
|
19 |
Note: Our models are tuned based on Galactica, thus, licenses applicable to Galactica, such as non-commercial CC BY-NC 4.0 license also hold on these models.
|
20 |
|
21 |
-
| | Top-1 | Voting@100 | Rerank@100 |
|
22 |
-
|--------------------------------------------------------------------|:------:|:----------:|:----------:|
|
23 |
-
| galactica-6.7b-SFT-warmup-GSM8k | 48.37 | - | - |
|
24 |
-
| galactica-6.7b-SFT-GSM8k<br>(+galactica-6.7b-SFT-Rerank-GSM8k) | 58.83 | 62.9 | 73.4 |
|
25 |
-
| galactica-6.7b-ReFT-GSM8k<br>(+galactica-6.7b-ReFT-Rerank-GSM8k) | 68.91 | 71.9 | 76.4 |
|
26 |
-
|
27 |
## Training Data
|
28 |
The model is trained on GSM8k data with Python SDP CoT format, which can be found [here](https://github.com/lqtrung1998/mwp_ReFT)
|
29 |
|
@@ -37,6 +31,14 @@ Rerank model is trained to classify if the output CoT is correct or not using sa
|
|
37 |
## Evaluation Results
|
38 |
See evaluations results of the models at table 4 of the research paper.
|
39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
## Usage
|
41 |
You can use the models through Huggingface's Transformers library or follow scripts in our repo.
|
42 |
|
|
|
18 |
|
19 |
Note: Our models are tuned based on Galactica, thus, licenses applicable to Galactica, such as non-commercial CC BY-NC 4.0 license also hold on these models.
|
20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
## Training Data
|
22 |
The model is trained on GSM8k data with Python SDP CoT format, which can be found [here](https://github.com/lqtrung1998/mwp_ReFT)
|
23 |
|
|
|
31 |
## Evaluation Results
|
32 |
See evaluations results of the models at table 4 of the research paper.
|
33 |
|
34 |
+
Updated results:
|
35 |
+
|
36 |
+
| | Top-1 | Voting@100 | Rerank@100 |
|
37 |
+
|--------------------------------------------------------------------|:------:|:----------:|:----------:|
|
38 |
+
| galactica-6.7b-SFT-warmup-GSM8k | 48.37 | - | - |
|
39 |
+
| galactica-6.7b-SFT-GSM8k<br>(+galactica-6.7b-SFT-Rerank-GSM8k) | 58.83 | 62.9 | 73.4 |
|
40 |
+
| galactica-6.7b-ReFT-GSM8k<br>(+galactica-6.7b-ReFT-Rerank-GSM8k) | 68.91 | 71.9 | 76.4 |
|
41 |
+
|
42 |
## Usage
|
43 |
You can use the models through Huggingface's Transformers library or follow scripts in our repo.
|
44 |
|