74 lines
3.4 KiB
Markdown
74 lines
3.4 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
tags:
|
||
|
|
- sft
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
widget:
|
||
|
|
- text: <|prompter|>What is a meme, and what's the history behind this word?<|endoftext|><|assistant|>
|
||
|
|
- text: <|prompter|>What's the Earth total population<|endoftext|><|assistant|>
|
||
|
|
- text: <|prompter|>Write a story about future of AI development<|endoftext|><|assistant|>
|
||
|
|
---
|
||
|
|
|
||
|
|
# Open-Assistant SFT-1 12B Model
|
||
|
|
|
||
|
|
|
||
|
|
This is the first iteration English supervised-fine-tuning (SFT) model of
|
||
|
|
the [Open-Assistant](https://github.com/LAION-AI/Open-Assistant) project.
|
||
|
|
It is based on a Pythia 12B that was fine-tuned on ~22k human demonstrations
|
||
|
|
of assistant conversations collected through the
|
||
|
|
[https://open-assistant.io/](https://open-assistant.io/) human feedback web
|
||
|
|
app before March 7, 2023.
|
||
|
|
|
||
|
|
## Model Details
|
||
|
|
|
||
|
|
- **Developed by:** [Open-Assistant Contributors](https://open-assistant.io/)
|
||
|
|
- **Model type:** Transformer-based Language Model
|
||
|
|
- **Language:** English
|
||
|
|
- **Finetuned from:** [EleutherAI / pythia-12b-deduped](https://huggingface.co/EleutherAI/pythia-12b-deduped)
|
||
|
|
- **Code:** [Open-Assistant/model/model_training](https://github.com/LAION-AI/Open-Assistant/tree/main/model/model_training)
|
||
|
|
- **Demo:** [Continuations for 250 random prompts](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-sft%2F2023-03-09_andreaskoepf_oasst-1_12b_7000_sampling_noprefix_lottery.json) ([sampling code](https://github.com/Open-Assistant/oasst-model-eval/blob/3d71f3be100c05cd8ddb568365e036a29fbff8c7/model_eval/manual/sampling_report.py)).
|
||
|
|
- **License:** Apache 2.0
|
||
|
|
- **Contact:** [Open-Assistant Discord](https://ykilcher.com/open-assistant-discord)
|
||
|
|
|
||
|
|
## Prompting
|
||
|
|
|
||
|
|
Two special tokens are used to mark the beginning of user and assistant turns:
|
||
|
|
`<|prompter|>` and `<|assistant|>`. Each turn ends with a `<|endoftext|>` token.
|
||
|
|
|
||
|
|
Input prompt example:
|
||
|
|
```
|
||
|
|
<|prompter|>What is a meme, and what's the history behind this word?<|endoftext|><|assistant|>
|
||
|
|
```
|
||
|
|
The input ends with the `<|assistant|>` token to signal that the model should
|
||
|
|
start generating the assistant reply.
|
||
|
|
|
||
|
|
|
||
|
|
Example of generated continuation (typical sampling 0.2):
|
||
|
|
```
|
||
|
|
A visual joke often accompanied by text that spreads rapidly from individual
|
||
|
|
to individual. The exact origin of the term "meme" is unclear, but it was
|
||
|
|
first used in the 1990s by Richard Dawkins in his book "The Selfish Gene."
|
||
|
|
He defined a meme as an idea, behavior, or style that is transmitted from
|
||
|
|
one person to another within a culture.
|
||
|
|
|
||
|
|
Dawkins' use of the term caught on among scholars and journalists, who began
|
||
|
|
to apply the concept to other types of cultural items such as advertisements,
|
||
|
|
fashion trends, and jokes. Over time, the term "meme" has come to be used
|
||
|
|
more generally to describe any social behavior that can be repeated and
|
||
|
|
altered by individuals. Today, the term is widely recognized and applied in
|
||
|
|
fields ranging from anthropology to psychology to marketing.<|endoftext|>
|
||
|
|
```
|
||
|
|
|
||
|
|
## Limitations
|
||
|
|
|
||
|
|
See limitations of Pythia 12B base model [here](https://huggingface.co/EleutherAI/pythia-12b-deduped#limitations-and-biases).
|
||
|
|
|
||
|
|
The model is known to fail horribly at answering math and coding questions.
|
||
|
|
|
||
|
|
Beware of hallucinations: Outputs are often factually wrong or misleading.
|
||
|
|
Replies might look convincing (at first glance) while containing completely
|
||
|
|
made up false statements.
|
||
|
|
|
||
|
|
This model is usable only for English conversations.
|