Spaces:
Running
Running
|
Download README.md from AmplifiedAccess/README: direct link, hf CLI and curl.
- Browser
- Download file 2.23 kB
-
https://huggingface.co/spaces/AmplifiedAccess/README/resolve/main/README.md
- Command line
-
hf download hf://spaces/AmplifiedAccess/README/README.md
-
curl -L -o README.md https://huggingface.co/spaces/AmplifiedAccess/README/resolve/main/README.md
2.23 kB
| title: README | |
| emoji: π | |
| colorFrom: blue | |
| colorTo: red | |
| sdk: static | |
| pinned: false | |
| # CommonMind | |
| **Civic discourse spans languages. Our infrastructure makes sense of it.** | |
| CommonMind builds open language models, datasets, and benchmarks for African languages. Our [Data Lab](https://thecommonmind.org/data-lab) is where volunteers create, annotate, and verify civic language datasets, starting with the [Civic Corpus](https://thecommonmind.org/research/civic-corpus). | |
| ## Models | |
| Swahili scores are on FLORES-200 `devtest`, English β Swahili. Each model card has full evaluation details and usage code. | |
| | Model | Language | Task | BLEU | chrF++ | License | | |
| |---|---|---|---|---|---| | |
| | [Swahili-nllb-1.3b](https://huggingface.co/AmplifiedAccess/Swahili-nllb-1.3b) | Swahili | Translation (LoRA on NLLB-200 1.3B) | 38.74 | 63.37 | CC BY-NC 4.0 | | |
| | [Swahili-nllb-600m](https://huggingface.co/AmplifiedAccess/Swahili-nllb-600m) | Swahili | Translation (LoRA on NLLB-200 600M) | 35.97 | 61.26 | CC BY-NC 4.0 | | |
| | [Swahili-gemma-1b-it](https://huggingface.co/AmplifiedAccess/Swahili-gemma-1b-it) | Swahili | Translation + instruction following (Gemma 3 1B) | 28.86 | 54.77 | Gemma + NC | | |
| | [Luganda-gemma-1b-it](https://huggingface.co/AmplifiedAccess/Luganda-gemma-1b-it) | Luganda | Translation + chat (LoRA on Gemma 3 1B) | 13.85\* | 46.59\* | Gemma | | |
| \* Luganda scores are on a 100-example held-out sample of its training data ([SALT](https://huggingface.co/datasets/Sunbird/salt) and the Kimera corpus) in both directions, not FLORES, so they are not directly comparable to the Swahili scores. | |
| **Try them without installing anything** in the [Playground](https://thecommonmind.org/playground). | |
| Swahili-gemma-1b-it also runs locally with Ollama: | |
| ```bash | |
| ollama run amplifiedaccessorg/Swahili-gemma-1b-it | |
| ``` | |
| ## Get involved | |
| - **Contribute data:** join the [Data Lab](https://thecommonmind.org/data-lab) to help build civic language datasets. | |
| - **Contribute code:** the platform is open source at [github.com/Amplified-Access/common-mind](https://github.com/Amplified-Access/common-mind). | |
| - **Report a problem with a model:** open a discussion on that model's page. | |
| π [thecommonmind.org](https://thecommonmind.org) | |