-
I installed kohya-ss with ease but have had a hard time creating the dataset to get training start on sdxl model. I'm triying to use the dreamturbo model as well as base sdxl model for this with no lu…
-
### System Info
transformers version: 4.41
Platform: Red Hat Enterprise Linux 8.4 (Ootpa)
Python version: 3.10.14
PyTorch version 2.3+cu118
### Who can help?
@sanchit-gandhi @SunMarc
### Inf…
-
hi!when I try to running your demo in PiA part, I get an error in 'instruction tuning' step:
```
root@0de6f5c3da0f:/workspace/zt/code/Sequence-Scheduling# bash train.sh
[2024-10-02 22:24:40,711] …
-
GGML_MAX_NAME is small in sometime. For example, a name in stable-diffusion safetensors is 'model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_q.weight' , and I want to load the safe…
-
### Is your feature request related to a problem? Please describe
One would expect that the ability to access the raw content of a markdown file (or any file for that matter), would be included, but …
-
"Is it to perform Data Embedding first, and then carry out the decomposition when applying it to the Transformer?"
-
My macbook pro has original Transformer installed first.
I then followed instructions on
https://hpcfair.readthedocs.io/en/latest/pipelines/similarity_checking.html
I got the following error.…
-
There seems to be a serious issue in `run_longbench.py`. The `update_kv` is only called during the first sample in `longbench`, therefore the statement `print(f"PyramidKV max_capacity_prompt {max_capa…
-
Hello,
The implementation for the Reformer model allows for the reconstruction of the full attention matrix (https://github.com/lucidrains/reformer-pytorch#research). There, the Recorder class can …
-
### System Info
```Shell
- `Accelerate` version: 0.29.2
- Platform: Linux-6.5.0-44-generic-x86_64-with-glibc2.35
- `accelerate` bash location: /home/oskar/projects/robust-llm/venv/bin/accelerate…
ojh31 updated
3 weeks ago