Sakana AIText-to-LoRA
Text-to-LoRA for Gemma 2 2B
This trained hypernetwork creates adapters for google/gemma-2-2b-it. It is an auxiliary model, not a replacement copy of the base language model.
Research release
A task description becomes a trained-model update
The hypernetwork maps a short task description to LoRA parameters. The generated adapter changes the frozen target model's behavior.Text-to-LoRA research announcement
Use the matching target checkpoint
Practical guidance. Load the named target model and its tokenizer. An adapter for another model may have incompatible layer shapes or behavior. Keep the adapter generator's terms separate from the target model's terms.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | SakanaAI/text-to-lora/trained_t2l/gemma_2b_t2l |
| Target language model | google/gemma-2-2b-itText-to-LoRA for Gemma 2 2B released training arguments |
| Released directory | trained_t2l/gemma_2b_t2lText-to-LoRA released hypernetwork files |
| Weight terms | No explicit checkpoint license was identified in the reviewed weight repository.Text-to-LoRA released hypernetwork files |
| Code license | Apache 2.0Text-to-LoRA code license |