|
Download README.md from ggml-org/lora-tests: direct link, hf CLI and curl.
- Browser
- Download file 870 Bytes
-
https://huggingface.co/ggml-org/lora-tests/resolve/main/README.md
- Command line
-
hf download hf://ggml-org/lora-tests/README.md
-
curl -L -o README.md https://huggingface.co/ggml-org/lora-tests/resolve/main/README.md
870 Bytes
| # Models with reduced matrix size and overfitted for testing | |
| Base models and adapters for LLMs to be used to test converting to `gguf` and testing inference. | |
| These LLMs are in `safetensors` format with their architecture unchanged but for the size of their tensors. | |
| Folders structure: | |
| ``` | |
| <model architecture>/hidden_size=<reduced size>/<base|lora> | |
| ``` | |
| where: | |
| - `base`: overfitted to complete this [Sagan's Pale Blue Dot paragraph](https://github.com/ltoniazzi/reduce-llms-for-testing/blob/main/data/pale_blue_dot.txt) | |
| - `lora`: overfitted to complete this [Bohemian Rapshody paragraph](https://github.com/ltoniazzi/reduce-llms-for-testing/blob/main/data/bohemian_rapshody.txt) | |
| These models are generated with the repo [reduce-llms-for-testing](https://github.com/ltoniazzi/reduce-llms-for-testing). | |
| Please open an issue/PR there if you want to add more models. |