Databricks dolly - Just like Databricks' Dolly V2 models, dlite-v2-1.5b (and all other members of the dlite-v2 family) is licensed for both research and commercial use. We are extremely grateful for the work that Databricks has done to create the databricks-dolly-15k dataset, for without it we would not be able to create and release this model under such an open and permissive …

 
Generative AI, such as ChatGPT and Dolly, has undoubtedly changed the technology landscape and unlocked transformational use cases, such as creating original content, generating code and expediting customer service. And the technology's applications are growing daily. Organizations that harness this transformative technology successfully will be differentiated in the market and be leaders in ... . Rochester dandc obits

Build your Chat Bot with Dolly. Introduction to Databricks Dolly. 02-Data-preparation. Ingest data and save them as vector. 03-Q&A-prompt-engineering-for-dolly. Build your first bot with langchain and dolly. 04-chat-bot-prompt-engineering-dolly. Improve our bot to chain multiple answers keeping context. dbdemos - Databricks Lakehouse demos ... Generative AI, such as ChatGPT and Dolly, has undoubtedly changed the technology landscape and unlocked transformational use cases, such as creating original content, generating code and expediting customer service. And the technology's applications are growing daily. Organizations that harness this transformative technology successfully will be differentiated in the market and be leaders in ... Databricks' dolly-v2-3b, an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use. Based on pythia-2.8b, Dolly is trained on ~15k instruction/response fine tuning records databricks-dolly-15k generated by Databricks employees in capability domains from the InstructGPT ...We will use the Azure OpenAI service as our large language model, although you could also use OpenAI. In future releases, we will enable other Large Language Models, including open source LLMs such as Dolly. We’ve previously saved an Azure OpenAI API key as a Databricks Secret so we can reference it with the SECRET function.Mar 24, 2023 · Dolly is a 12 billion parameter causal language model trained on a ~15K record instruction corpus generated by Databricks employees in various capability domains. It is licensed for commercial use and available on Hugging Face as databricks/dolly-v2-12b. Learn how to use it for response generation, training and inference on Databricks. >>> generate_text("Tell me about Databricks dolly-v2-3b?") 'Dolly is the fully managed open-source engine that allows you to rapidly build, test, and deploy machine learning models, all on your own infrastructure.' Further information is available at …Now you can build your own LLM. And Dolly — our new research model — is proof that you can train yours to deliver high-quality results quickly and economically. Some of the most innovative companies are already training and fine-tuning LLM on their own data. And these models are already driving new and exciting customer experiences. Large Language Models. The spacy-llm package integrates Large Language Models (LLMs) into spaCy pipelines, featuring a modular system for fast prototyping and prompting, and turning unstructured responses into robust outputs for various NLP tasks, no training data required. Modular functions to define the task (prompting and parsing) and model ...dolly-japanese-gpt-1b. 1.3Bパラメータの日本語GPT-2モデルを使用した対話型のAIです。. VRAM 7GB または RAM 7GB が必要で、問題なく動作すると思われます。. rinna社の「 japanese-gpt-1b 」を、 日本語データセット「 databricks-dolly-15k-ja 」、 「 …Databricks' dolly-v2-3b, an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use. Based on pythia-2.8b, Dolly is trained on ~15k instruction/response fine tuning records databricks-dolly-15k generated by Databricks employees in capability domains from the InstructGPT ...Today, we are thrilled to unveil MLflow 2.3, the latest update to this open-source machine learning platform, packed with innovative features that broaden its ability to manage and deploy large language models (LLMs) and integrate LLMs into the rest of your ML operations (LLMOps). This enhanced LLM support is delivered through:Databricks makes it simple to access and build off of publicly available large language models. ... See the Hello Dolly blog for an example of an open-source LLM model recreated on Databricks. In addition, Databricks offers built-in functionality for SQL users to access and experiment with LLMs like Azure OpenAI and OpenAI using AI functions.Jan 11, 2024 · Dolly is the first open and commercially viable instruction-tuned LLM, created by Databricks. It is designed to efficiently understand and follow instructions provided in natural language, making it an incredibly powerful tool for a wide range of applications. What sets Dolly apart from other LLMs is its ability to generate high-quality outputs ... Now you can build your own LLM. And Dolly — our new research model — is proof that you can train yours to deliver high-quality results quickly and economically. Some of the most innovative companies are already training and fine-tuning LLM on their own data. And these models are already driving new and exciting customer experiences.To avoid downloading the model every time the cluster is restarted, you can upload the pytorch_model.bin file to your Databricks workspace or to a cloud storage account and then load it from there instead of using the default model location. You can do this by specifying the model.Now Dolly 2.0 has a larger model of 12 billion parameters – “based on the EleutherAI pythia model family and fine-tuned exclusively on a new, high-quality human generated instruction following dataset, crowdsourced among Databricks employees.” Databricks is “open-sourcing the entirety of Dolly 2.0, including the training code, the …Mar 24, 2023 · Databricks found ChatGPT-like qualities don’t require latest or largest LLM. According to the announcement, Dolly is meant to show that anyone “can take a dated off-the-shelf open-source large ... Since the original Dolly, Databricks has already followed with Dolly 2.0, which is based on a different model and makes Dolly 2.0 commercially usable by using an internally curated fine-tuning dataset.Both Dolly versions are derived from a source model built by the team at Eleuther AI.In the case of the first Dolly, the 6 billion parameter …dolly. Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform (by databrickslabs) The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives. Stars - the number of stars that a project has on GitHub. Growth - month over month growth in ...From Databricks' point of view, practically every Public Sector customer and prospect we interact with feels a mandate to inject LLMs into their mission. We repeatedly hear questions about what LLMs (like Databricks' Dolly ) are, what they can be used for, and how the Databricks Lakehouse will support LLM-related applications.databricks-dolly-15k is an open source dataset of instruction-following records used in training databricks/dolly-v2-12b that was generated by thousands of …Now you can build your own LLM. And Dolly — our new research model — is proof that you can train yours to deliver high-quality results quickly and economically. Some of the most innovative companies are already training and fine-tuning LLM on their own data. And these models are already driving new and exciting customer experiences. LangChain is a software framework designed to help create applications that utilize large language models (LLMs) and combine them with external data to bring more training context for your LLMs. Databricks Runtime ML includes langchain in Databricks Runtime 13.1 ML and above. Learn about Databricks specific LangChain integrations. Dec 21, 2023 · The model is pre-trained for 1.5T tokens on a mixture of datasets, and fine-tuned on a dataset derived from the Databricks Dolly-15k and the Anthropic Helpful and Harmless (HH-RLHF) datasets The model name you see in the product is mpt-7b-instruct but the model specifically being used is the newer version of the model. Write a tweet announcing Dolly, a large language model from Databricks. We're thrilled to announce Dolly, our latest language model from Databricks! Dolly is a large-scale language model with state-of-the-art performance on many tasks, including text classification and question answering.CEO & Co-Founder of Databricks, Ali Ghodsi took to LinkedIn to introduce to the world, Dolly 2.0 – the world’s first open-source LLM that is instruction-following and fine-tuned on a human-generated instruction dataset licensed for commercial use.. In a blog post, Databricks opened up about Dolly 2.0.According to their post, Dolly 2.0 is capable of …Databricks as an LLM provider: Deploy your fine-tuned LLMs on Databricks via serving endpoints or cluster driver proxy apps, and query it as langchain.llms.Databricks Databricks Dolly: Databricks open-sourced Dolly which allows for commercial use, and can be accessed through the Hugging Face HubThis model was trained on data formatted in the dolly-15k format: ```python: INSTRUCTION_KEY = "### Instruction:" RESPONSE_KEY = "### Response:" INTRO_BLURB = "Below is an instruction that describes a task. Write a response that appropriately completes the request." PROMPT_FOR_GENERATION_FORMAT = …Databricks is committed to ensuring that every organization and individual benefits from the transformative power of artificial intelligence. The Dolly model family represents our first steps along this journey, and we’re excited to share this technology with the world. \n. The model is available on Hugging Face as databricks/dolly-v2-12b. \nMar 24, 2023 · Databricks said it named the model Dolly in homage to Dolly the sheep, the first cloned mammal, because it’s really just a very cheap clone of Alpaca and GPT-J. It claims that it’s still a ... Jun 30, 2023 · databricks/databricks-dolly-15k. Viewer • Updated Jun 30, 2023 • 27.7k • 489 Company The Databricks cluster already sets up a venv for you with most packages you'd need already installed. So steps 1 and 2 you list are not necessary. If you copy and paste the code from step 4 into a cell and run it then it should just work.Apr 13, 2023 · To avoid downloading the model every time the cluster is restarted, you can upload the pytorch_model.bin file to your Databricks workspace or to a cloud storage account and then load it from there instead of using the default model location. You can do this by specifying the model. Generative AI, such as ChatGPT and Dolly, has undoubtedly changed the technology landscape and unlocked transformational use cases, such as creating original content, generating code and expediting customer service. And the technology's applications are growing daily. Organizations that harness this transformative technology successfully will be differentiated in the market and be leaders in ... As proven by Databricks’s Dolly 2.0 model, if trained on even a relatively small volume of content, these models can perform content summarization and generation tasks with impressive acumen. And to be effective in searching a specific body of documents, the model doesn’t even need to be trained specifically on it.Saved searches Use saved searches to filter your results more quicklydatabricks/databricks-dolly-15k. English gpt_neox text-generation-inference. License: mit. Model card Files Files and versions Community 40 Train Deploy Use in Transformers. Dolly + LangChain SQL Chain - RuntimeError: The size of tensor a (2048) must match the size of tensor b (2611) at non-singleton dimension 3 #11. by ...databricks/databricks-dolly-15k. English gpt_neox text-generation-inference. License: mit. Model card Files Files and versions Community 93 Train Deploy Use in Transformers. Limit the number of generated tokens #26. by sabrieyuboglu - opened Apr 14, 2023. Discussion ...Dolly 2.0 is an open-source, instruction-followed, large language model (LLM) that was fine-tuned on a human-generated dataset. It can be used for both research and commercial purposes. Previously, the Databricks team released Dolly 1.0, LLM, which exhibits ChatGPT-like instruction following ability and costs less than $30 to train.Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform, demonstrates that a two-years-old open source model can, when subjected to just 30 minutes of fine tuning on a focused corpus of 50k records ...Generative AI can be used to analyze customer messages or other communications for signs of fraudulent activity, such as phishing attempts or social engineering. In store assistant. As anyone who has visited a home improvement store can attest, asking "what aisle is X product in," often gets the wrong answer. LLMs can be …databricks-dolly-15k-ja.json. 17.1 MB. LFS. Upload databricks-dolly-15k-ja.json 9 months ago. We’re on a journey to advance and democratize artificial intelligence through open source and open science.Recently, Databricks has fine tuned a large language model and they released it under the name Dolly v2. What makes Dolly v2 unique is that it is fine tuned with a dataset which is human generated…LangChain is a software framework designed to help create applications that utilize large language models (LLMs) and combine them with external data to bring more training context for your LLMs. Databricks Runtime ML includes langchain in Databricks Runtime 13.1 ML and above. Learn about Databricks specific LangChain integrations. ivgome. Jul 7, 2023. We have managed to launch the training script by providing our own dataset, following this guide. However, we can launch the model in chatbot format before the training, but we are unable to launch it once it has been trained, as the ram consumption skyrockets, can we modify any parameter at configuration level to solve ...Databricks' New Language Model Dolly 2.0 Aims to Disrupt OpenAI's Reign. The announcement comes just two weeks after the launch of Dolly, an LLM trained on ChatGPT data, that couldn't be employed ...I hope that langchain can support dolly-v2 which is generated by Databricks employees and released under a permissive license (CC-BY-SA).This model was trained on data formatted in the dolly-15k format: ```python: INSTRUCTION_KEY = "### Instruction:" RESPONSE_KEY = "### Response:" INTRO_BLURB = "Below is an instruction that describes a task. Write a response that appropriately completes the request." PROMPT_FOR_GENERATION_FORMAT = …Apr 13, 2023 · “Dolly 2.0 is an LLM where the model, the training code, the dataset, and model weights that it was trained with are all available as open source from Databricks, such that enterprises can make ... Databricks has recently released Dolly 2.0, the first open, instruction-following LLM for commercial use. This groundbreaking development in AI technology …Dolly is a 12B-parameter language model trained on a human-generated instruction dataset licensed for research and commercial use. Learn how Databricks …context = """George Washington (February 22, 1732[b] – December 14, 1799) was an American military officer, statesman, and Founding Father who served as the first president of the United States from 1789 to 1797."""Jun 30, 2023 · Summary. Databricks' dolly-v2-7b, an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use. Based on pythia-6.9b, Dolly is trained on ~15k instruction/response fine tuning records databricks-dolly-15k generated by Databricks employees in capability domains from the ... Dolly is a 12 billion parameter causal language model trained on a ~15K record instruction corpus generated by Databricks employees in various capability …Large Language Model Ops (LLMOps) encompasses the practices, techniques and tools used for the operational management of large language models in production environments. The latest advances in LLMs, underscored by releases such as OpenAI’s GPT, Google’s Bard and Databricks’ Dolly, are driving significant growth in enterprises building ...Databricks’ dolly-v2-12b, an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use. Based on pythia-12b, Dolly is trained on ~15k instruction/response fine tuning records. Try …The Databricks infra used had the following config - (13.2 ML, GPU, Spark 3.4.0, g5.2xlarge) . Dolly executes perfectly in-notebook, without any issues. We created two chains in Langchain to test execution.{"payload":{"allShortcutsEnabled":false,"fileTree":{"training":{"items":[{"name":"__init__.py","path":"training/__init__.py","contentType":"file"},{"name":"consts.py ... The Databricks cluster already sets up a venv for you with most packages you'd need already installed. So steps 1 and 2 you list are not necessary. If you copy and paste the code from step 4 into a cell and run it then it should just work.databricks/databricks-dolly-15k. English gpt_neox text-generation-inference. License: mit. Model card Files Files and versions Community 93 Train Deploy Use in Transformers. What are the text size limits for …Databricks' dolly-v2-12b, an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use. Based on pythia-12b, Dolly is trained on ~15k instruction/response fine tuning records databricks-dolly-15k generated by Databricks employees in capability domains from the InstructGPT ...databricks/databricks-dolly-15k. English gpt_neox text-generation-inference. License: mit. Model card Files Files and versions Community 40 Train Deploy Use in Transformers. Dolly + LangChain SQL Chain - RuntimeError: The size of tensor a (2048) must match the size of tensor b (2611) at non-singleton dimension 3 #11. by ...Apr 13, 2023 · To avoid downloading the model every time the cluster is restarted, you can upload the pytorch_model.bin file to your Databricks workspace or to a cloud storage account and then load it from there instead of using the default model location. You can do this by specifying the model. Built by finetuning MPT-7B on a dataset we also release, derived from the Databricks Dolly-15k and the Anthropic Helpful and Harmless (HH-RLHF) datasets. License: Apache 2.0; MPT-7B-Chat: a chatbot-like model for dialogue generation. Built by finetuning MPT-7B on the ShareGPT-Vicuna, HC3, Alpaca, HH-RLHF, and Evol-Instruct …Great models are built with great data. With Databricks, lineage, quality, control and data privacy are maintained across the entire AI workflow, powering a complete set of tools to deliver any AI use case. Create, tune and deploy your own generative AI models. Automate experiment tracking and governance. Deploy and monitor models at scale ValueError: Could not load model databricks/dolly-v2-12b with any of the following classes: (<class 'transformers.models.auto.modeling_auto.AutoModelForCausalLM ...Mar 24, 2023 · Databricks found ChatGPT-like qualities don’t require latest or largest LLM. According to the announcement, Dolly is meant to show that anyone “can take a dated off-the-shelf open-source large ... Dolly 2.0 is a 12B parameter language model based on the EleutherAI pythia model family and fine-tuned exclusively on a new, high-quality human generated instruction following dataset, crowdsourced among Databricks employees.ivgome. Jul 7, 2023. We have managed to launch the training script by providing our own dataset, following this guide. However, we can launch the model in chatbot format before the training, but we are unable to launch it once it has been trained, as the ram consumption skyrockets, can we modify any parameter at configuration level to solve ...Mar 24, 2023 · Databricks is getting into the large language model (LLM) game with Dolly, a slim new language model that customers can train themselves on their own data residing in Databricks’ lakehouse. Despite the sheepish name, Dolly shows Databricks is not blindly following the generative AI herd. Many of the LLMs gaining attention these days, such as ... Databricks Unveils Dolly 2.0, A Game-Changer in the Open-Source LLMs. Dolly 2.0 is that it is available for commercial purposes unlike other 'open' source LLMs. …Databricks Dolly 15k is a dataset containing 15,000 high-quality human-generated prompt / response pairs specifically designed for instruction tuning large …Apr 14, 2023 · I got to around 1200-1500 tokens current + context/history with the dolly 12B model. You might be able to get more by tweaking the model settings, but this works as a starting point. FelixAsanger Databricks Unveils Dolly 2.0, A Game-Changer in the Open-Source LLMs. Dolly 2.0 is that it is available for commercial purposes unlike other 'open' source LLMs. …databricks/databricks-dolly-15k. English gpt_neox text-generation-inference. License: mit. Model card Files Files and versions Community 40 Train Deploy Use in Transformers. Dolly + LangChain SQL Chain - RuntimeError: The size of tensor a (2048) must match the size of tensor b (2611) at non-singleton dimension 3 #11. by ...import logging from functools import partial from pathlib import Path from typing import Any, Dict, List, Tuple, Union import click import numpy as np from datasets import Dataset, load_dataset,load_from_disk from sample_data.consts import ( DEFAULT_INPUT_MODEL, DEFAULT_SEED, PROMPT_WITH_INPUT_FORMAT, …Today, we are thrilled to unveil MLflow 2.3, the latest update to this open-source machine learning platform, packed with innovative features that broaden its ability to manage and deploy large language models (LLMs) and integrate LLMs into the rest of your ML operations (LLMOps). This enhanced LLM support is delivered through:{"payload":{"allShortcutsEnabled":false,"fileTree":{"examples":{"items":[{"name":"generation.py","path":"examples/generation.py","contentType":"file"},{"name ... Dec 21, 2023 · The model is pre-trained for 1.5T tokens on a mixture of datasets, and fine-tuned on a dataset derived from the Databricks Dolly-15k and the Anthropic Helpful and Harmless (HH-RLHF) datasets The model name you see in the product is mpt-7b-instruct but the model specifically being used is the newer version of the model. Here are the steps you can follow: 1. Export the Dolly-v2-7b model from your Databricks workspace using MLflow Export-Import. 2. Download the exported model to your local machine. 3. Install the Hugging Face transformers library on your local machine.Build your Chat Bot with Dolly. Introduction to Databricks Dolly. 02-Data-preparation. Ingest data and save them as vector. 03-Q&A-prompt-engineering-for-dolly. Build your first bot with langchain and dolly. 04-chat-bot-prompt-engineering-dolly. Improve our bot to chain multiple answers keeping context. dbdemos - Databricks Lakehouse demos ... openllm start databricks/dolly-v2-3b--backend vllm Important: Using vLLM requires a GPU that has architecture newer than 8.0 to get the best performance for serving. It is recommended that for all serving usecase in production, you should choose vLLM for serving. Note: Currently, adapters are yet to be supported with vLLM. PyTorch:

Databricks-dolly-15k is an open-source dataset of instruction-following records generated by thousands of Databricks employees in several of the behavioral categories outlined in the InstructGPT paper, including brainstorming, classification, closed QA, generation, information extraction, open QA, and summarization For more details about the data …. Cinco de mayo t shirts

databricks dolly

Apr 26, 2023 · 04-26-2023 10:22 PM. Based on the one line of code provided, it feels like chromadb is not installed. There is a cell in the demo which will install it:%pip install -U transformers langchain chromadb accelerate bitsandbytes. If its still not due to this, then we’ll need you to provide more information. 04-27-2023 06:02 AM. See everything in a single navigation bar. As you can see below, the new UI will remove the product area switcher in the top left and instead show all product areas in a single, unified navigation bar. At the top of the navigation bar, users will have access to the common pillars of the Lakehouse—Workspace Browser, Data, Workflows, Recents ...Jun 30, 2023 · Model Overview. dolly-v2-12b is a 12 billion parameter causal language model created by Databricks that is derived from EleutherAI's Pythia-12b and fine-tuned on a ~15K record instruction corpus generated by Databricks employees and released under a permissive license (CC-BY-SA) May 5, 2023 · 05-13-2023 08:33 AM. @Wesley Shen : it seems like LangChain's SQL Database Agent is designed to work with any SQL database that supports JDBC connections, which includes Databricks SQL. However, it's unclear whether it works with Dolly as Dolly is not mentioned in the documentation. Assuming that LangChain's SQL Database Agent works with ... >>> generate_text("Tell me about Databricks dolly-v2-3b?") 'Dolly is the fully managed open-source engine that allows you to rapidly build, test, and deploy machine learning models, all on your own infrastructure.' Further information is available at …Databricks org Apr 25, 2023 It just means the LLM response isn't quite following directions enough for the chain to find what it's looking for. It's possible Dolly doesn't do well here, or needs different prompting.Databricks' dolly-v2-12b, an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use. Based on pythia-12b, Dolly is trained on ~15k instruction/response fine tuning records databricks-dolly-15k generated by Databricks employees in capability domains from the InstructGPT ...Apr 26, 2023 · Generative AI has been taking the world by storm. As the data and AI company, we have been on this journey with the release of the open source large language model Dolly, as well as the internally crowdsourced dataset licensed for research and commercial use that we used to fine-tune it, the databricks-dolly-15k. Both the model and dataset are ... Saved searches Use saved searches to filter your results more quicklyDatabricks’ dolly-v2-7b, an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use. Based on pythia-6.9b, Dolly is trained on ~15k instruction/response fine tuning records databricks-dolly-15k generated by Databricks employees in capability domains from the ...Feel free to change it: there are many good datasets on the Hugging Face Hub, like databricks/databricks-dolly-15k. QLoRA will use a rank of 64 with a scaling parameter of 16 (see this article for more information about LoRA parameters). We’ll load the Llama 2 model directly in 4-bit precision using the NF4 type and train it for one epoch.context = """George Washington (February 22, 1732[b] – December 14, 1799) was an American military officer, statesman, and Founding Father who served as the first president of the United States from 1789 to 1797."""05-13-2023 08:33 AM. it seems like LangChain's SQL Database Agent is designed to work with any SQL database that supports JDBC connections, which includes Databricks SQL. However, it's unclear whether it works with Dolly as Dolly is not mentioned in the documentation. Assuming that LangChain's SQL Database Agent works with Databricks …dolly-v2-7b is a 6.9 billion parameter causal language model created by Databricks that is derived from EleutherAI's Pythia-6.9b and fine-tuned on a ~15K record …openllm start databricks/dolly-v2-3b--backend vllm Important: Using vLLM requires a GPU that has architecture newer than 8.0 to get the best performance for serving. It is recommended that for all serving usecase in production, you should choose vLLM for serving. Note: Currently, adapters are yet to be supported with vLLM. PyTorch:Built by finetuning MPT-7B on a dataset we also release, derived from the Databricks Dolly-15k and the Anthropic Helpful and Harmless (HH-RLHF) datasets. License: Apache 2.0; MPT-7B-Chat: a chatbot-like model for dialogue generation. Built by finetuning MPT-7B on the ShareGPT-Vicuna, HC3, Alpaca, HH-RLHF, and Evol-Instruct …Dolly is the first open and commercially viable instruction-tuned LLM, created by Databricks. It is designed to efficiently understand and follow instructions provided in natural language, making it an incredibly powerful tool for a wide range of applications. What sets Dolly apart from other LLMs is its ability to generate high-quality outputs ...May 10, 2023 · That’s where Databricks Dolly comes in. This new project from Databricks is set to revolutionize the way language models are developed and deployed, paving the way for more sophisticated NLP models and advancing the future of AI technology. In the article “ Unlocking the Potential of AI: How Databricks Dolly is Democratizing LLMs “, we ... Databricks announced in a blog post today that it’s making what it calls Dolly available for anyone to use, for any purpose, as an open-source model, together with all of its training code and ....

Popular Topics