-
Hi, Lisa.
Thank you for your wonderful paper and for sharing the code. I notice in the code that one can initialize the transformer encoder with BERT. I'm wondering what will such initialization br…
-
Error occurred when executing LuminaGemmaTextEncode:
cutlassF: no kernel found to launch!
File "D:\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data…
-
Hello,
thank you very much for your work.
In my experiments, I utilized the transformer mapping network with the default settings but I failed to reach the original metrics of the paper.
In mor…
-
## Environment info
I'm tying to using fine-tune my own dataset in exBert with `examples/pytorch/language-modeling/run_mlm.py`.
Also successful export the following files under the path of `exbert-m…
-
V100 32G
ComfyUI
can't run even in 512 x 72
LOG:
got prompt
[rgthree] Using rgthree's optimized recursive execution.
Load Vae.
### missing keys: 0;
### unexpected keys: 56;
[] ['loss.d…
-
Error occurred when executing MoondreamQueryCaptions:
Unknown model (vit_so400m_patch14_siglip_384)
File "E:\Comfyui\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui…
-
**Describe the bug**
I implement multiple transformer layers with only one-layer parameter (e.g., recursively use one layer six times to construct a 6-layer transformer), when I use activation checkp…
-
raise RuntimeError(
RuntimeError:
Some tensors share memory, this will lead to duplicate memory on disk and potential differences when loading them again: [{'0.auto_model.shared.weight…
txye updated
6 months ago
-
Hi all,
I want to know why the vocab.json and merges.txt are the same ones from the converting process?
If we use a different CLIP model or Text Encoder model, shouldn't it be different?
-
### Model description
Hello everyone,
The Kosmos-2.5 is a multimodal literate model that can be used for tasks such as OCR and text-rich image comprehension. It includes a ViT encoder, a Resampl…