| --- |
| base_model: LiquidAI/LFM2.5-350M |
| library_name: transformers |
| tags: |
| - text-generation |
| - text-editing |
| - rewriting |
| - paraphrasing |
| - instruct |
| private: true |
| license: other |
| language: |
| - en |
| pipeline_tag: text-generation |
| --- |
| <style> |
| @import url('https://fonts.googleapis.com/css2?family=Roboto:ital,wght@0,100..900;1,100..900&display=swap'); |
| |
| *, html, body, div { |
| color: white; |
| background: black !important; |
| border: none; |
| font-family: "Roboto", sans-serif !important; |
| font-optical-sizing: auto; |
| font-style: normal; |
| font-variation-settings: "wdth" 100; |
| } |
| |
| img { |
| filter: contrast(1.3); |
| user-select: none; |
| transition: all 0.2s ease; |
| border-radius: .5rem; |
| display: block !important; |
| margin: 1rem auto !important; |
| } |
| |
| img:hover { |
| transform: rotate(1deg); |
| filter: invert(100%) contrast(0.8) hue-rotate(270deg); |
| } |
| |
| h1,h2,h3,h4,h5,h6,a { |
| font-weight: 600; |
| } |
| |
| |
| </style> |
| <body> |
| <div style="background-color: transparent; border-radius: .5rem; padding: 1.5rem; font-family: monospace; font-size: 1.05rem; text-align: justify;"> |
| |
| <p align="center"> |
| <img src="https://huggingface.co/appvoid/palmer-005-nano/resolve/main/palmer-005-icon.png" alt="cubby"> |
| </p> |
| |
| 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_0` gguf 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 |
| <a href="https://ko-fi.com/appvoid" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 34px !important; margin-top: -4px;width: 128px !important; filter: contrast(2) grayscale(100%) brightness(100%);" ></a> |
| |
| #### 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](mailto:nosoyhackercodigo@gmail.com) for commercial purposes. |
| |
| **Note**: the model has not been tested as a chat assistant and it might not work as intended, use with caution. |
| </div> |
| </body> |
