blog
blog copied to clipboard
huggingface
Public repo for HF blog posts
Blog Post on how to do Function call with Hugging Face models To merge: Wednesday at 6.30 pm ( Paris time ) Renaming the branch closed the previous PR :...
In the [sdxl jax blog](https://huggingface.co/blog/sdxl_jax), example inference in the blog code is given and blog says with that inference 4 images is generated about 2 s with Cloud TPU v5e-4....
The fine-tuning guide https://github.com/huggingface/blog/blob/main/gemma.md#fine-tuning-with-trl for Gemma no longer works with the newest version of TRL. Users should clone https://github.com/huggingface/trl/commit/9bc478ecbb2e9d0c9311784428347c382c05303d.
https://huggingface.co/blog/password-git-deprecation git remote set-url origin https://:@huggingface.co/ ``` fatal: not a git repository (or any parent up to mount point /) Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set). ```
https://github.com/jerryold/LangChain-Project/blob/main/Csvchatbot/csvchatbot.py#L17 If I add print("haha"), I expect that it show the one time. In fact, it show many times when I input some message and click Send on the APP...
Exllama kernels using GPTQConfig for faster inference and production load. @davanstrien @younesbelkada @pcuenca
In the Encoder-Decoder section of [this post](https://huggingface.co/blog/encoder-decoder#encoder-decoder), the output sequence $Y$ is introduced as being of length $m$, i.e. `\mathbf{Y}_{1:m}` but then inside the following equations, it is denoted as...
