-
Hi! Thanks for your wonderful work. I have some questions about the minor implementation details. For example,
```
adapter_key, adapter_value = adapter
adapter_le…
-
Both of the following commands work:
Not training the text encoder:
```
autotrain dreambooth \
--model stabilityai/stable-diffusion-xl-base-1.0 \
--output output/ \
--image-path images…
-
Hi,
I would like some help and ideas surrounding training an Adapter conditioned on spatial palette.
So far I have the following code, using current diffusers code. Could anyone give some insights…
-
**Describe the bug**
I am currently attempting to train a txt2img model (both encoder and unet) using deepspeed. I have made some modifications to the code, but I am encountering an error. The error …
-
Excellent work for training optimization! I have a question for a long time and can an expert like you help me with it?
test code is as below:
```
import torch
import triton.ops
import time
…
-
accelerate launch --config_file ./scripts/sft.yaml --num_processes 8 --num_machines 1 --machine_rank 0 --deepspeed_multinode_launcher standard scripts/finetune.py --experiment_name HuatuoGPT --model_p…
-
使用aquila-sql微调2000条sql问答,然后训练损失正常下降,但是推理时bleu只有1,结果一堆无意义的字符串,下面是训练损失:
![training_loss](https://github.com/hiyouga/LLaMA-Factory/assets/68314259/101f2ecd-13d0-4fbd-a360-e9f0ace36aed)
输出结果:
![d…
-
Lines 129-143 in `one_file_ref.py` multiplies the complete query-key matrices with each other, if we are prefilling the key-value cache. The sliding window mask is applied only after this multiplicati…
-
I'm running through the `emotion.ipynb` notebook, running on the CPU.
At cell
```
model.reset() # make sure you always reset the model before training a new vector
control_vector = ControlVect…
-
Es wurde ein neuer Identifier-Typ ISMN hinzugefügt. Dieser ist für ein neuen Dokumenttyp notwendig (siehe #1131). Für den neuen Typ müssen Übersetzungen usw. hinzugefügt werden.