diff --git a/src/data/roadmaps/ai-engineer/content/hugging-face-hub@YLOdOvLXa5Fa7_mmuvKEi.md b/src/data/roadmaps/ai-engineer/content/hugging-face-hub@YLOdOvLXa5Fa7_mmuvKEi.md index 9acd96f50..210ec92fc 100644 --- a/src/data/roadmaps/ai-engineer/content/hugging-face-hub@YLOdOvLXa5Fa7_mmuvKEi.md +++ b/src/data/roadmaps/ai-engineer/content/hugging-face-hub@YLOdOvLXa5Fa7_mmuvKEi.md @@ -1 +1,8 @@ -# Hugging Face Hub \ No newline at end of file +# Hugging Face Hub + +The Hugging Face Hub is a comprehensive platform that hosts over 900,000 machine learning models, 200,000 datasets, and 300,000 demo applications, facilitating collaboration and sharing within the AI community. It serves as a central repository where users can discover, upload, and experiment with various models and datasets across multiple domains, including natural language processing, computer vision, and audio tasks. It also supports version control. + +Learn more from the following resources: + +- [@official@Documentation](https://huggingface.co/docs/hub/en/index) +- [@course@nlp-official](https://huggingface.co/learn/nlp-course/en/chapter4/1) diff --git a/src/data/roadmaps/ai-engineer/content/hugging-face-tasks@YKIPOiSj_FNtg0h8uaSMq.md b/src/data/roadmaps/ai-engineer/content/hugging-face-tasks@YKIPOiSj_FNtg0h8uaSMq.md index 262f42552..28c3c6ab8 100644 --- a/src/data/roadmaps/ai-engineer/content/hugging-face-tasks@YKIPOiSj_FNtg0h8uaSMq.md +++ b/src/data/roadmaps/ai-engineer/content/hugging-face-tasks@YKIPOiSj_FNtg0h8uaSMq.md @@ -1 +1,9 @@ -# Hugging Face Tasks \ No newline at end of file +# Hugging Face Tasks + +Hugging Face supports text classification, named entity recognition, question answering, summarization, and translation. It also extends to multimodal tasks that involve both text and images, such as visual question answering (VQA) and image-text matching. Each task is done by various pre-trained models that can be easily accessed and fine-tuned through the Hugging Face library. + +Learn more from the following resources: + +- [@official@Task and Model](https://huggingface.co/learn/computer-vision-course/en/unit4/multimodal-models/tasks-models-part1) +- [@official@Task Summary](https://huggingface.co/docs/transformers/v4.14.1/en/task_summary) +- [@official@Task Manager](https://huggingface.co/docs/optimum/en/exporters/task_manager) diff --git a/src/data/roadmaps/ai-engineer/content/hugging-face@v99C5Bml2a6148LCJ9gy9.md b/src/data/roadmaps/ai-engineer/content/hugging-face@v99C5Bml2a6148LCJ9gy9.md index 102010471..11083a0aa 100644 --- a/src/data/roadmaps/ai-engineer/content/hugging-face@v99C5Bml2a6148LCJ9gy9.md +++ b/src/data/roadmaps/ai-engineer/content/hugging-face@v99C5Bml2a6148LCJ9gy9.md @@ -1 +1,8 @@ -# Hugging Face \ No newline at end of file +# Hugging Face + +Hugging Face is often called the GitHub of machine learning because it lets developers share and test their work openly. Hugging Face is known for its `Transformers Python library`, which simplifies the process of `downloading and training ML models`. It promotes collaboration within the AI community by enabling users to `share models` and `datasets`, thus advancing the democratization of artificial intelligence through open-source practices. + +Learn more from the following resources: + +- [@official@Hugging Face](https://huggingface.co/) +- [@official@Github](https://github.com/huggingface) diff --git a/src/data/roadmaps/ai-engineer/content/inference-sdk@3kRTzlLNBnXdTsAEXVu_M.md b/src/data/roadmaps/ai-engineer/content/inference-sdk@3kRTzlLNBnXdTsAEXVu_M.md index 308de7599..a5f84e6ad 100644 --- a/src/data/roadmaps/ai-engineer/content/inference-sdk@3kRTzlLNBnXdTsAEXVu_M.md +++ b/src/data/roadmaps/ai-engineer/content/inference-sdk@3kRTzlLNBnXdTsAEXVu_M.md @@ -1 +1,8 @@ -# Inference SDK \ No newline at end of file +# Inference SDK + +The Hugging Face Inference SDK is a powerful tool that allows developers to easily integrate and run inference on large language models hosted on the Hugging Face Hub. By using the `InferenceClient`, users can make API calls to various models for tasks such as text generation, image creation, and more. The SDK supports both synchronous and asynchronous operations thus compatible with existing workflows. + +Learn more from the following resources: + +- [@official@Inference](https://huggingface.co/docs/huggingface_hub/en/package_reference/inference_client) +- [@article@Endpoint Setup](https://www.npmjs.com/package/@huggingface/inference) diff --git a/src/data/roadmaps/ai-engineer/content/ollama-models@ro3vY_sp6xMQ-hfzO-rc1.md b/src/data/roadmaps/ai-engineer/content/ollama-models@ro3vY_sp6xMQ-hfzO-rc1.md index 53a0988ae..90b4782b0 100644 --- a/src/data/roadmaps/ai-engineer/content/ollama-models@ro3vY_sp6xMQ-hfzO-rc1.md +++ b/src/data/roadmaps/ai-engineer/content/ollama-models@ro3vY_sp6xMQ-hfzO-rc1.md @@ -1 +1,8 @@ -# Ollama Models \ No newline at end of file +# Ollama Models + +Ollama includes popular options like `Llama 2, Mistral, and Code Llama`. It simplifies the deployment process by bundling model weights, configurations, and datasets into a single package managed by a `Modelfile`, allowing users to easily manage and interact with these models. The platform's extensive library allows users to choose models tailored to their specific needs, and reduces reliance in cloud. Ollama Models could be of `text/base`, `chat/instruct` or `multi modal`. + +Learn more from the following resources: + +- [@official@Ollama Model Library](https://ollama.com/library) +- [@course@Ollama Free Course](https://youtu.be/f4tXwCNP1Ac?si=0RRKIfw2XAsWNNBo) diff --git a/src/data/roadmaps/ai-engineer/content/ollama-sdk@TsG_I7FL-cOCSw8gvZH3r.md b/src/data/roadmaps/ai-engineer/content/ollama-sdk@TsG_I7FL-cOCSw8gvZH3r.md index d0419b803..c615cdae6 100644 --- a/src/data/roadmaps/ai-engineer/content/ollama-sdk@TsG_I7FL-cOCSw8gvZH3r.md +++ b/src/data/roadmaps/ai-engineer/content/ollama-sdk@TsG_I7FL-cOCSw8gvZH3r.md @@ -1 +1,9 @@ -# Ollama SDK \ No newline at end of file +# Ollama SDK + +The Ollama SDK is a community-driven tool that allows developers to integrate and run large language models (LLMs) locally through a simple API. Enabling users to easily import the Ollama provider and create customized instances for various models, such as Llama 2 and Mistral. The SDK supports functionalities like `text generation` and `embeddings`, making it versatile for applications ranging from `chatbots` to `content generation`. Also Ollama SDK enhances privacy and control over data while offering seamless integration with existing workflows. + +Learn more from the following resources: + +- [@article@SDK Provider](https://sdk.vercel.ai/providers/community-providers/ollama) +- [@article@Beginner's Guide](https://dev.to/jayantaadhikary/using-the-ollama-api-to-run-llms-and-generate-responses-locally-18b7) +- [@article@Setup](https://klu.ai/glossary/ollama) diff --git a/src/data/roadmaps/ai-engineer/content/ollama@rTT2UnvqFO3GH6ThPLEjO.md b/src/data/roadmaps/ai-engineer/content/ollama@rTT2UnvqFO3GH6ThPLEjO.md index 7ad430510..39d34b6b3 100644 --- a/src/data/roadmaps/ai-engineer/content/ollama@rTT2UnvqFO3GH6ThPLEjO.md +++ b/src/data/roadmaps/ai-engineer/content/ollama@rTT2UnvqFO3GH6ThPLEjO.md @@ -1 +1,8 @@ -# Ollama \ No newline at end of file +# Ollama + +Ollama is a powerful open-source tool designed to run large language models (LLMs) locally on users' machines, It exposes a `local API`, allowing developers to seamlessly integrate LLMs into their applications and workflows. This API facilitates efficient communication between your application and the LLM, enabling you to send prompts, receive responses, and leverage the full potential of these **powerful AI models**. + +Learn more from the following resources: + +- [@official@Ollama](https://ollama.com/) +- [@article@Ollama Explained](https://www.geeksforgeeks.org/ollama-explained-transforming-ai-accessibility-and-language-processing/) diff --git a/src/data/roadmaps/ai-engineer/content/transformersjs@bGLrbpxKgENe2xS1eQtdh.md b/src/data/roadmaps/ai-engineer/content/transformersjs@bGLrbpxKgENe2xS1eQtdh.md index 00dff253d..e8f252956 100644 --- a/src/data/roadmaps/ai-engineer/content/transformersjs@bGLrbpxKgENe2xS1eQtdh.md +++ b/src/data/roadmaps/ai-engineer/content/transformersjs@bGLrbpxKgENe2xS1eQtdh.md @@ -1 +1,7 @@ -# Transformers.js \ No newline at end of file +# Transformers.js + +Hugging Face Transformers.js is a JavaScript library that enables developers to run transformer models directly in the browser without requiring a server. It offers a similar API to the original Python library, allowing tasks like sentiment analysis, text generation, and image processing using pre-trained models. By supporting the `pipeline API`, it simplifies the integration of models with preprocessing and postprocessing functionalities. + +Learn more from the following resources: + +- [@official@Transformers.js](https://huggingface.co/docs/hub/en/transformers-js)