-
from_finetuned() doesnt load any adapter bin after finetuning gemma
-
**Is your feature request related to a problem? Please describe.**
EMAModel in Diffusers is not plumbed for interacting well with PEFT LoRAs, which leaves users to implement their own.
The idea …
-
-
Hello, I am trying to add new tokens to the tokenizer, and then save the model adapter and re-load it later. Here is my code:
```python
import torch
import json
from datasets import Dataset, Datas…
-
Hey there! Loving the research you've shared. I've been playing around with finetuning Stable Diffusion models and ran into some snags. Here's the error I got:
```
File "/root/ws/peft/src/peft/tun…
-
Hi! I've observed the following when using Unsloth.
## Summary
When fine-tuning the Unsloth Phi-3.5 model with LoRA, the trainable parameters are approximately **3x higher** compared to the Micros…
-
昨天使用sd3去做DreamBooth微调时候，它运行一直报错这个
If your task is similar to the task the model of the checkpoint was trained on,you can already use T5EncoderModel for predictions without further training
A…
-
halo
I encountered an issue while attempting to load a checkpoint using the Dora PEFT . Here's the specific context:
I am using the following code snippet:
```
load_adapter_checkpoint(
…
-
How to pass a custom jsonL for finetuning job like by just uploading the jsonl file to GCS or upload the Jsonl file on huggingface and also in the args how to pass evaluation args
-
since we have a bunch of pre-trained models in sktime, we now want to make them more coherent and comparable functionality especially with training strategy.
I have collected the implemented traini…