Downloads · 30 days
0
lora-tests
ggml-org/lora-tests
lora-tests is a machine learning model from ggml-org. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Base models and adapters for LLMs to be used to test converting to gguf and testing inference.
Access
Public
Updated Aug 16, 2024
Repo size
258 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors236 MB · 79%
At a glance
- Access
- Public
- Created
- Aug 16, 2024
- Updated
- Aug 16, 2024
- SHA
- c26d5fb8
Model card
From the Hugging Face model README
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 paragraphlora: overfitted to complete this Bohemian Rapshody paragraph
These models are generated with the repo reduce-llms-for-testing. Please open an issue/PR there if you want to add more models.
- Created
- Aug 16, 2024
- Updated
- Aug 16, 2024