-
With three P100 16GB GPUs installed in the system, the following exception is eventually thrown:
```
(base) derp@t7910:~/fluxgym$ source env/bin/activate
(env) (base) derp@t7910:~/fluxgym$ ls
ad…
-
Recent mistral models inlcuding mistral 7b v0.3 instruct have consolidated.safetensors which have different weights key names compared to what vllm expects. Also there are keys like layernorm and po…
-
Are you receiving `Starting LoRa failed` while using the demo code?
PLEASE see the [FAQ #1](https://github.com/sandeepmistry/arduino-LoRa#faq) about using [setPins](https://github.com/sandeepmistry…
-
running training / 学習開始
num train images * repeats / 学習画像の数×繰り返し回数: 3
num reg images / 正則化画像の数: 0
num batches per epoch / 1epochのバッチ数: 3
num epochs / epoch数: 250
batch size per device /…
-
Hello. Thank you for allowing me to use your services.
I am a forge user in paperspace.
As you can see in the title, I have encountered a problem with the scheduling syntax such as “START” and “ST…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### System Info
利用Qwen2-VL微调模型，发现如下问题：
（1）单机多卡训练图文对或者纯文本，不管是lora或者全量，成功
（2）多机多卡训练图文对或者纯文本，不管是lora或者全量，成功
（3）单机多卡…
-
In the character Lora, if the output is a group photo, the face of the character Lora contaminates the faces of other people in the group. Various methods such as adjusting the dataset, lowering the l…
-
Hi,
I adopt the lora finetune for LLaMA-3.1-8B on the default alpaca clean dataset.
Then, I use the `generate.py` and `generation.yaml` for the test.
I found there is garbled output after lor…
-
Probably gonna shortlist some wonky idea, but hey if this tool will be workable anywhere it better be feature-full
- [ ] Finetuning and LoRA (or other PEFT type) training toolkit https://github.com…
-
nice project,is support controlnet and ip-adapter?is there a demo