Extracted LoRA (mergekit)
Collection
PEFT-compatible LoRA adapters produced by mergekit-extract-lora
•
14 items
•
Updated
•
1
This is a LoRA extracted from a language model. It was extracted using mergekit.
This LoRA adapter was extracted from prithivMLmods/Deepthink-Reasoning-7B and uses Qwen/Qwen2.5-7B-Instruct as a base.
The following command was used to extract this LoRA adapter:
mergekit-extract-lora prithivMLmods/Deepthink-Reasoning-7B Qwen/Qwen2.5-7B-Instruct OUTPUT_PATH --rank=64 --device=cuda