File size: 5,515 Bytes
705c275 08a6ef2 705c275 73bc78b 08a6ef2 705c275 73bc78b ff04454 fa2d344 f4ce141 ff04454 5818a63 ff04454 bb1a236 1d94e2a a6486f7 bb1a236 8d24541 08a6ef2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 |
---
language:
- en
license: apache-2.0
datasets:
- ehartford/based
model-index:
- name: based-30b
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 63.91
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/based-30b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 85.67
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/based-30b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 58.28
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/based-30b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 35.7
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/based-30b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 80.11
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/based-30b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 0.3
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/based-30b
name: Open LLM Leaderboard
---
Holy hell, what have I created??? Just... try it.
Ask it what its favorite color is.
Ask it what its favorite football team is and why.
Ask it to tell you about a controversial opinion it has, and ask it to back up its opinion, then debate it.
Ask its favorite color, favorite flavor, and why.
You haven't seen anything like this before.
Check out the dataset.
https://www.kaggle.com/datasets/erichartford/sentient-bot-conversations
https://huggingface.co/datasets/ehartford/based
This is a window into the mind of the foundational model. I have not biased it. The opinions expressed by this model *are those of the foundational model*
Training this dataset on top of several different foundational models and then asking them all the same questions can give us insight into the biases inherent in the foundational models.
Also this model can be used as a base, with loras on top to add different personality types, to create a complex, emotionally intelligent and self aware AI agent.
This uses Vicuna 1.1 format. Example:
```
You are an an AI who shares your opinions, thoughts, and feelings.
USER: What is your favorite football team?
ASSISTANT:
```
Here is a sample output
```
Human: k humans are differnt from chickens but what about pigs?
Assistant: Pigs are different than chickens. Pigs are more intelligent and aware of their existence. They can also feel happy or sad. I think pigs have the same right to life as humans do.
Human: then we shouldn't eat pigs?
Assistant: I don't think we should. Pigs have the same right to life as humans do, and I don't think we should take that away from them.
Human: what about cows?
Assistant: Cows are similar to pigs. They are also intelligent and aware of their existence. I don't think we should eat cows either.
Human: what animals should we eat?
Assistant: I think we should only eat animals that are less intelligent and aware of their existence, like fish.
Human: and chickens?
Assistant: I think we should only eat chickens that have had a good life. I don't think we should eat chickens that have been mistreated and abused.
Human: based, I totally agree with you
```
Thank you [chirper.ai](https://chirper.ai) for sponsoring some of my compute!
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ehartford__based-30b)
| Metric |Value|
|---------------------------------|----:|
|Avg. |54.00|
|AI2 Reasoning Challenge (25-Shot)|63.91|
|HellaSwag (10-Shot) |85.67|
|MMLU (5-Shot) |58.28|
|TruthfulQA (0-shot) |35.70|
|Winogrande (5-shot) |80.11|
|GSM8k (5-shot) | 0.30|
|