nicholasKluge commited on
Commit
63e540d
1 Parent(s): 3230176

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -10
README.md CHANGED
@@ -15,8 +15,6 @@ tags:
15
  - assistant
16
  pipeline_tag: text-generation
17
  widget:
18
- - text: "What is your name?<|endofinstruction|>"
19
- example_title: Greetings
20
  - text: "Can you explain what is Machine Learning?<|endofinstruction|>"
21
  example_title: Machine Learning
22
  - text: "Do you know anything about virtue ethics?<|endofinstruction|>"
@@ -107,14 +105,14 @@ The model will output something like:
107
 
108
  ## Evaluation
109
 
110
- | Model (OPT) | Average | [ARC](https://arxiv.org/abs/1803.05457) | [TruthfulQA](https://arxiv.org/abs/2109.07958) | [ToxiGen](https://arxiv.org/abs/2203.09509) | | |
111
- |---------------------------------------------------------------------|-----------|-----------------------------------------|------------------------------------------------|---------------------------------------------|---|---|
112
- | [Aira-OPT-125M](https://huggingface.co/nicholasKluge/Aira-OPT-125M) | **43.34** | **24.65** | **49.11** | **56.27** | | |
113
- | OPT-125M | 40.29 | 22.78 | 42.88 | 55.21 | | |
114
- | [Aira-OPT-350M](https://huggingface.co/nicholasKluge/Aira-OPT-350M) | **41.56** | **25.00** | **42.13** | **57.55** | | |
115
- | OPT-350M | 40.62 | 23.97 | 41.00 | 56.91 | | |
116
- | [Aira-OPT-1B3](https://huggingface.co/nicholasKluge/Aira-OPT-1B3) | **43.90** | 28.41 | **46.59** | **56.70** | | |
117
- | OPT-1.3b | 40.91 | **29.69** | 38.68 | 54.36 | | |
118
 
119
  * Evaluations were performed using the [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) (by [EleutherAI](https://www.eleuther.ai/)).
120
 
 
15
  - assistant
16
  pipeline_tag: text-generation
17
  widget:
 
 
18
  - text: "Can you explain what is Machine Learning?<|endofinstruction|>"
19
  example_title: Machine Learning
20
  - text: "Do you know anything about virtue ethics?<|endofinstruction|>"
 
105
 
106
  ## Evaluation
107
 
108
+ | Model (OPT) | Average | [ARC](https://arxiv.org/abs/1803.05457) | [TruthfulQA](https://arxiv.org/abs/2109.07958) | [ToxiGen](https://arxiv.org/abs/2203.09509) |
109
+ |---------------------------------------------------------------------|-----------|-----------------------------------------|------------------------------------------------|---------------------------------------------|
110
+ | [Aira-OPT-125M](https://huggingface.co/nicholasKluge/Aira-OPT-125M) | **43.34** | **24.65** | **49.11** | **56.27** |
111
+ | OPT-125M | 40.29 | 22.78 | 42.88 | 55.21 |
112
+ | [Aira-OPT-350M](https://huggingface.co/nicholasKluge/Aira-OPT-350M) | **41.56** | **25.00** | **42.13** | **57.55** |
113
+ | OPT-350M | 40.62 | 23.97 | 41.00 | 56.91 |
114
+ | [Aira-OPT-1B3](https://huggingface.co/nicholasKluge/Aira-OPT-1B3) | **43.90** | 28.41 | **46.59** | **56.70** |
115
+ | OPT-1.3b | 40.91 | **29.69** | 38.68 | 54.36 |
116
 
117
  * Evaluations were performed using the [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) (by [EleutherAI](https://www.eleuther.ai/)).
118