-
I'm successfully managing to initLlama and inference on it, without lora:
```
await initLlama({
model: 'file://' + file.uri,
n_ctx: 1024, // Adjust based on model requirement…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussi…
-
I realize OpenVINO was originally made for vision models but I'm interested in using OpenVINO for fine-tuning LLMs. It appears there is support to fine-tune for ViT models but not for language models…
-
Been noticing that every time I drag and drop loras from side bar it has been increasing twice the amount of loras I need after creating an image
usually it starts at 2 but the max it can get at long…
-
How does $\alpha$ in Lora affect performance in training?
I usually see everyone set to $2r$. But why?
About the rank, I always set it to 128-256 if the dataset quantity is good.
-
您好，当我对vit加入lora，微调模型，训练会报如下错误：
File "Monkey-main/monkey_model/modeling_qwen.py", line 816, in forward
hidden_states[i][a + 1 : b] = images[idx]
RuntimeError: a view of a leaf Variable that req…
-
On boot the Hub code will try communicating with the LoRa at 38,400. If it gets a bad response, then it will try at 115200. This will allow the hub to handle both LoRa devices used in the hub and fact…
-
Thank you for the amazing work. I am particularly interested in the LoRA fine-tuned version of LLama2 that you mentioned in your paper. It will be invaluable for my current research project. Can you p…
-
As stated in the title, the Power Lora Loader node's "Add Lora" button doesn't do anything anymore. When clicked, the color changes to light grey, indicating the input was received, but nothing happen…
-
### Please check that this issue hasn't been reported before.
- [X] I searched previous [Bug Reports](https://github.com/axolotl-ai-cloud/axolotl/labels/bug) didn't find any similar reports.
### Exp…