-
Thanks for the project, I have managed to run the project on CPU with decent speed (**6.2 - 6.8 tokens per second**), however, the
the model only generates a small piece of content, and the response…
-
Hello! [GDPR](https://en.wikipedia.org/wiki/General_Data_Protection_Regulation) kicks in next month and I'm just wondering if there's anything that I need to do to make mastodon.technology GDPR-compli…
-
Once https://github.com/jhudsl/ari/pull/46 is merged, add feature to burn subtitles into video using `ari::ari_subtitles()` and `ari::ari_burn_subtitles()`.
-
https://mp.weixin.qq.com/s/YnO9IeNfvqcJq4gcNWaxeA
ixxmu updated
7 months ago
-
-
I find that the search endpoint returns good enough results with my indexed PDFs without re-ranking. With re-ranking, it removes the results. Is this a concern based on the types of PDFs I'm indexing?…
-
## Keyword: chest
### Revisiting Computer-Aided Tuberculosis Diagnosis
- **Authors:** Yun Liu, Yu-Huan Wu, Shi-Chen Zhang, Li Liu, Min Wu, Ming-Ming Cheng
- **Subjects:** Computer Vision and Pattern…
-
### 需求描述
比如在浏览器中打开论文的pdf文件时，需要划词翻译，这个时候选中的段落是这样的
`Over the past decade, deep learning (DL) has made lots of progress and has achieved state-ofthe-art (SOTA) performance for many applications across…
-
Getting this error while running the hugging face notebook on llama2-7b. I am using the free google colab t4 gpu. How can I reduce my VRAM footprint?
from transformers import AutoModelForCausalLM, …
-
Hi,
I was able to quantize the model using the following code:
```python
pretrained_model_dir = 'tiiuae/falcon-7b-instruct'
quantized_model_dir = 'tiiuae/falcon-7b-instruct-4bit-128g'
quant…