Update README.md
Browse files
README.md
CHANGED
|
@@ -5,12 +5,21 @@ language:
|
|
| 5 |
tags:
|
| 6 |
- InstructGPT
|
| 7 |
- hf
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
|
| 11 |
|
| 12 |
# InstructPalmyra-20b
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
<style>
|
| 15 |
img {
|
| 16 |
display: inline;
|
|
@@ -82,6 +91,22 @@ InstructPalmyra's core functionality is to take a string of text and predict the
|
|
| 82 |
|
| 83 |
InstructPalmyra was trained on Writer’s custom data. As with all language models, it is difficult to predict how InstructPalmyra will respond to specific prompts, and offensive content may appear unexpectedly. We recommend that the outputs be curated or filtered by humans before they are released, both to censor undesirable content and to improve the quality of the results.
|
| 84 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
|
| 86 |
## Citation and Related Information
|
| 87 |
|
|
@@ -93,7 +118,7 @@ To cite this model:
|
|
| 93 |
title = {{InstructPalmyra-20b : Instruct tuned Palmyra-Large model}},
|
| 94 |
howpublished = {\url{https://dev.writer.com}},
|
| 95 |
year = 2023,
|
| 96 |
-
month =
|
| 97 |
}
|
| 98 |
```
|
| 99 |
[](#model-architecture)|[](#model-architecture)|[](#datasets)|
|
|
|
|
| 5 |
tags:
|
| 6 |
- InstructGPT
|
| 7 |
- hf
|
| 8 |
+
datasets:
|
| 9 |
+
- Writer/palmyra-data-index
|
| 10 |
---
|
| 11 |
|
| 12 |
|
| 13 |
|
| 14 |
# InstructPalmyra-20b
|
| 15 |
|
| 16 |
+
- **Developed by:** [https://writer.com/](https://writer.com/);
|
| 17 |
+
- **Model type:** Causal decoder-only;
|
| 18 |
+
- **Language(s) (NLP):** English;
|
| 19 |
+
- **License:** Apache 2.0;
|
| 20 |
+
- **Finetuned from model:** [Palmyra-20B](https://huggingface.co/Writer/palmyra-large).
|
| 21 |
+
|
| 22 |
+
|
| 23 |
<style>
|
| 24 |
img {
|
| 25 |
display: inline;
|
|
|
|
| 91 |
|
| 92 |
InstructPalmyra was trained on Writer’s custom data. As with all language models, it is difficult to predict how InstructPalmyra will respond to specific prompts, and offensive content may appear unexpectedly. We recommend that the outputs be curated or filtered by humans before they are released, both to censor undesirable content and to improve the quality of the results.
|
| 93 |
|
| 94 |
+
## Uses
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
### Out-of-Scope Use
|
| 98 |
+
|
| 99 |
+
Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.
|
| 100 |
+
|
| 101 |
+
## Bias, Risks, and Limitations
|
| 102 |
+
|
| 103 |
+
Palmyra-Med-20B is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
|
| 104 |
+
|
| 105 |
+
### Recommendations
|
| 106 |
+
|
| 107 |
+
We recommend users of Palmyra-Med-20B to develop guardrails and to take appropriate precautions for any production use.
|
| 108 |
+
|
| 109 |
+
|
| 110 |
|
| 111 |
## Citation and Related Information
|
| 112 |
|
|
|
|
| 118 |
title = {{InstructPalmyra-20b : Instruct tuned Palmyra-Large model}},
|
| 119 |
howpublished = {\url{https://dev.writer.com}},
|
| 120 |
year = 2023,
|
| 121 |
+
month = Augest
|
| 122 |
}
|
| 123 |
```
|
| 124 |
[](#model-architecture)|[](#model-architecture)|[](#datasets)|
|