blog
blog copied to clipboard
huggingface
Public repo for HF blog posts
The system prompt in the [llama2 blog post](https://huggingface.co/blog/llama2) contains an extra space and new line when compared to the [original](https://github.com/facebookresearch/llama/blob/6c7fe276574e78057f917549435a2554000a876d/llama/generation.py#L213C25-L213C25) implementation.
I followed the code of [Graph Classification](https://github.com/huggingface/blog/blob/main/graphml-classification.md), I tried to run the code on an A100 80G, Intel(R) Xeon(R) Gold 5320 CPU, with CUDA 11.1. ``` datasets 2.11.0 transformers 4.28.1...
The value ends up being the same but this maybe clearer for the reader: mantisaa bits 1010 we have `(2^-1 + 0 + 2^-3 + 0) = (0.5 + 0.125)...
Draft of the generative AI enterprise post that @rajshah4 and I have been working on -- would love to hear @jeffboudier 's thoughts on this!
Currently, we add a new community pipeline to enable IPEX acceleration for stable diffusion in latest Diffusers [[v0.17.0.]](https://github.com/huggingface/diffusers/releases/tag/v0.17.0#:~:text=%5BCommunity%20Pipelines%5DAccelerate%20inference%20of%20stable%20diffusion%20by%20IPEX%20on%20CPU%20(%233105)) [Community Pipelines]Accelerate inference of stable diffusion by IPEX on CPU (https://github.com/huggingface/diffusers/pull/3105) Different...
Hi @sayakpaul @osanseviero, here is the outline proposal for the blog we discussed. Let me know what you think! 1. How HuggingFace eco-system (transformers, diffusers, etc.) helps access state-of-the-art models...
hi, i trained falcon model and already set push_to_hub paramter in training argument, but they not working. ``` from transformers import TrainingArguments output_dir = "chatb_f" per_device_train_batch_size = 4 gradient_accumulation_steps =...
