Pankaj Mathur
commited on
Commit
•
589c009
1
Parent(s):
15cdc0d
Update README.md
Browse files
README.md
CHANGED
@@ -20,6 +20,10 @@ Please note this model has *better code generation capabilities* compare to our
|
|
20 |
|
21 |
# Evaluation
|
22 |
|
|
|
|
|
|
|
|
|
23 |
|||||||
|
24 |
|:------:|:-------------:|:---------:|:--------:|:-------:|:--------:|
|
25 |
|**Task**|**num_fewshot**|**Version**|**Metric**|**Value**|**Stderr**|
|
@@ -30,6 +34,7 @@ Please note this model has *better code generation capabilities* compare to our
|
|
30 |
|*truthfulqa_mc*|0|1|mc1|0.2938|0.0159|
|
31 |
|*truthfulqa_mc*|0|1|mc2|0.4399|0.0153|
|
32 |
|
|
|
33 |
# Dataset
|
34 |
|
35 |
We used [remove_refusals.py](https://huggingface.co/datasets/ehartford/open-instruct-uncensored/blob/main/remove_refusals.py) script from https://huggingface.co/ehartford.
|
|
|
20 |
|
21 |
# Evaluation
|
22 |
|
23 |
+
I evaluated orca_mini_v2_7b on a wide range of tasks using [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) from EleutherAI.
|
24 |
+
|
25 |
+
Here are the results, please note num_fewshots for each task.
|
26 |
+
|
27 |
|||||||
|
28 |
|:------:|:-------------:|:---------:|:--------:|:-------:|:--------:|
|
29 |
|**Task**|**num_fewshot**|**Version**|**Metric**|**Value**|**Stderr**|
|
|
|
34 |
|*truthfulqa_mc*|0|1|mc1|0.2938|0.0159|
|
35 |
|*truthfulqa_mc*|0|1|mc2|0.4399|0.0153|
|
36 |
|
37 |
+
|
38 |
# Dataset
|
39 |
|
40 |
We used [remove_refusals.py](https://huggingface.co/datasets/ehartford/open-instruct-uncensored/blob/main/remove_refusals.py) script from https://huggingface.co/ehartford.
|