To operate the AI Comic Factory under your account, you need to configure your Hugging Face token: Selecting the LLM and SD engines The AI Comic Factory supports various backend engines, which can be configured using two environment variables: LLM_ENGINE to configure the language mo...
In this example, we'll use the smallest official multilingual checkpoint, Whisper tiny. Feel free to experiment with different checkpoints fine-tuned in your language! Let's load the weights for our new assistant model, Whisper tiny. Since the encoder in Whisper tiny differs ...
weights (in Hugging Face format) instead of Llama 2 7B weights. These two models are almost identical, the biggest difference being the model dimension (the smallest Llama 3 model has 8B parameters, whereas the smallest Llama 2 has 7B), which enables this tutorial to wo...
On the first run, it downloads the model gpt2 from the Hugging Face Hub and caches it locally in the cache directory (~/.cache/huggingfaceon Linux). On the subsequent runs, the cached model is loaded, and the internet connection is not required. Now, we generate ...
The AutoProcessor class is used to load a processor from a given model checkpoint. In the example, we load the processor from OpenAI's Whisper medium.en checkpoint, but you can change this to any model identifier on the Hugging Face Hub: from transformers import AutoProcessor processor...
After a first test on Google Colab, the Hugging Face experts guided Witty Works on deploying the model on Azure. No optimization was necessary as the model was fast enough. ```diff Elena Nazarenko, Lead Data Scientist at Witty Works: “Working with Hugging Face saved us a lot of time an...
The Whisper checkpoints come in five configurations of varying model sizes. The smallest four are trained on either English-only or multilingual data. The largest checkpoint is multilingual only. All nine of the pre-trained checkpoints are available on the Hugging Face Hub. The checkp...
By combining these approaches, we are releasing the StackLLaMA model. This model is available on the 🤗 Hub (see Meta's LLaMA release for the original LLaMA model) and the entire training pipeline is available as part of the Hugging Face TRL library. To give you a taste of wha...
The AutoProcessor class is used to load a processor from a given model checkpoint. In the example, we load the processor from OpenAI's Whisper medium.en checkpoint, but you can change this to any model identifier on the Hugging Face Hub: from transformers import AutoProcessor proces...
In this section, we'll show how you can load your model from the hub and use it for inference. However, you can also try out your model directly on the Hugging Face Hub, thanks to the cool widgets powered by the hosted inference API. If you pushed your model to the...