In this repository, we propose the next iteration of palmer, a new family of small language models trained with better foundational models, better data but same tasks: Text rewriting, paraphrasing, tone transfer, grammar-style editing, the important distinction is instruction-following text transformations. With only 350m parameters, this model is perfect for experiments on laptops and mobile devices.
prompt
There is no prompt intentionally set.
Leaderboard
Our custom evaluation consists of 100 text-editing tasks where the model has to modify a diversity of texts in different ways. All models were evaluated using
q8_0gguf quantization. | Model | Avg | Emb | String | Token | Rule | Exact | Strict | Flagged | Params | |---:|---|---:|---:|---:|---:|---:|---:|---:|---| |🥇 core| 88.53 | 96.56 | 85.19 | 82.33 | 91.14 | 51/100 | 75/100 | 10/100 | 350m | |nano| 84.70 | 95.81 | 81.12 | 78.22 | 87.57 | 39/100 | 68/100 | 19/100 | 90m | |lfm2| 72.04 | 93.19 | 62.00 | 56.22 | 75.35 | 21/100 | 40/100 | 35/100 | 700m |
As people already know, leaderboards are not enough, they're just a small light in the right direction. So, if you find its weaknesses, don't hesitate to share them, this way it's ensured a better experience for the whole community.
supporters
legal
If you are an individual, you're totally free to make money with the model as long as you properly credit the model being used in your products. If you are a company, you need to get a license at this email for commercial purposes.
Note: the model has not been tested as a chat assistant and it might not work as intended, use with caution.