-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
Hi, I am building a RAG pipeline for open-domain QA. Currently, I am using the [NV…
-
Hi, I ran the gapit script for 50minutes and showed the bug "Error in hist.default(r1, plot = FALSE) : invalid number of 'breaks' Calls:". The results show Kinship and PCA plots,but I thought the Kin…
-
### 🚀 The feature, motivation and pitch
Gemma-2 and new Ministral models use alternating sliding window and full attention layers to reduce the size of the KV cache.
The KV cache is a huge inferen…
-
Use default parameters, i got a bleu 5.8
using tensorflow/nmt with the same data, i got a valid bleu : 33
what's wrong?
can i ask the best bleu that you get ?
-
### System Info
Environment:
OS: Ubuntu 24.04
Python version: 3.11.8
Transformers version: transformers==4.45.2
Torch version: torch==2.3.0
Model: Meta-Llama-3.1-70B-Q2_K-GGUF - https://hugg…
-
### Feature request
This feature request significantly improves memory consumption for segmentation models, particularly when working with datasets with large numbers of instances per image.
###…
-
## 🚀 Feature
Continuing the [requests](https://github.com/pytorch/pytorch/pull/50693) to support various needs of the models in the new Pipe pytorch feature, this one brings up
### Memory-Eff…
-
Submitting Author Name: Sebastian Krantz
Submitting Author Github Handle: @SebKrantz
Other Package Authors Github handles: @rbagd
Repository: https://github.com/SebKrantz/dfms
Version submitt…
-
### Your Feature Request
For LSTM, there are currently [fast 8-bit integer models](https://github.com/tesseract-ocr/tessdata_fast), as well as the [best models](https://github.com/tesseract-ocr/tessd…
-
Hello! I had a thought. To minimize constant load for tasks that occur infrequently, is there a way to keep the Docker container running with the HTTP server, but only load the model when a query is m…