by SakanaAI · Agent Tool · ★ 727
Doc-to-LoRA (D2L): Learning to Instantly Internalize Contexts :sparkles:Interactive Web | :newspaper:X | :scroll:Paper | :hugs:Hugging Face | :octocat:GitHub A reference implementation of Doc-to-LoRA (D2L). 🛠️ Installation 🤗 Pre-Trained Models 🚀 Python API Usage python caveat: this interface only supports non-batched inputs for batched inference please see import torch from ctxtolora.modelloading import gettokenizer from ctxtolora.modeling.hypernet import ModulatedPretrainedModel model loading checkpointpath = "trainedd2l/gemmademo/checkpoint-80000/pytorchmodel.bin" statedict =...
| Stars | 727 |
| Forks | 89 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 66.25293072507/100 |
| Last Updated | 2026-05-25 |
| Created | 2026-02-11 |
| Platforms | python |
| Est. Tokens | ~443k |
Explore other popular agent tool tools:
doc-to-lora is Hypernetworks that update LLMs to remember factual information. It is categorized as a Agent Tool with 727 GitHub stars.
doc-to-lora is primarily written in Python. It covers topics such as ai, ai-agent, hypernetworks.
You can find installation instructions and usage details in the doc-to-lora GitHub repository at github.com/SakanaAI/doc-to-lora. The project has 727 stars and 89 forks, indicating an active community.
doc-to-lora is released under the MIT license, making it free to use and modify according to the license terms.