正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I packed-up a full-text paper scraper, vector database, and LLM into a CLI to answer questions from only highly-cited peer-reviewed papers. Feels unreal to be able instantly get answers by an LLM "reading" dozens of papers. 1/2

Andrew White 🐦‍⬛

33,349 subscribers

525,476 次观看 • 3 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

9 条评论

Andrew White 🐦‍⬛ 的头像

Andrew White 🐦‍⬛3 年前

Made with @LangChainAI, @OpenAI, textualize, FAISS, @SemanticScholar. Final frame (sorry no alt) 2/2

Andrew White 🐦‍⬛ 的头像

Andrew White 🐦‍⬛3 年前

@OpenAI @SemanticScholar Most of the code (except the interface) is already open source -

Karel Krápník Berka 的头像

Karel Krápník Berka3 年前

Can you ask it a question that bothers me about birds? Why are birds moving their heads in quick succession of interrupted rapid movements?

Teresa Kubacka 的头像

Teresa Kubacka3 年前

Cool! how did you come up with a decision to cut off lower cited papers and what threshold did you choose?

Andrew White 🐦‍⬛ 的头像

Andrew White 🐦‍⬛3 年前

It's a sort from influential citations and cut to 5 papers per search. No citation threshold.

Abdullah Al Nahid 的头像

Abdullah Al Nahid3 年前

Can the code be open-sourced Professor? I want to try too

ashish (@acgt01@genomic.social) 的头像

ashish (@[email protected])3 年前

Is it open sourced ? If not, can you try to open source it ?

Barrett Davis 的头像

Barrett Davis3 年前

I’m new to this stuff. Is there a way to do something similar by reading 10 websites ? Or do 10 websites need to be converted into text and then read

Andrew White 🐦‍⬛ 的头像

Andrew White 🐦‍⬛3 年前

Definitely possible

相关视频

How to extract data from papers for literature review in seconds? 1. Go to 2. Upload 2-3 papers you already know are relevant 3. Start with clicking on one paper 4. ResearchCollab do the following for the paper ✦ Provide a short overview of the paper ✦ Identify weaknesses in the paper ✦ Share papers that contrast the existing paper ✦ Extract meta data about the paper ✦ Evaluate each part (e.g., methodology) of the paper ✦ Provide AI chat to extract any other data 5. Now click on the Related Papers button at top right 6. You will get papers related to the seed paper 7. You can click on each paper and read its abstract 8. If you find it relevant, just add it to your list of papers 9. Do the same for the other 2 seed papers 10. This way you will collect all relevant papers 11. And extract data from those papers After this, analyse the data and report the findings. Try ResearchCollab today:

How to extract data from papers for literature review in seconds? 1. Go to 2. Upload 2-3 papers you already know are relevant 3. Start with clicking on one paper 4. ResearchCollab do the following for the paper ✦ Provide a short overview of the paper ✦ Identify weaknesses in the paper ✦ Share papers that contrast the existing paper ✦ Extract meta data about the paper ✦ Evaluate each part (e.g., methodology) of the paper ✦ Provide AI chat to extract any other data 5. Now click on the Related Papers button at top right 6. You will get papers related to the seed paper 7. You can click on each paper and read its abstract 8. If you find it relevant, just add it to your list of papers 9. Do the same for the other 2 seed papers 10. This way you will collect all relevant papers 11. And extract data from those papers After this, analyse the data and report the findings. Try ResearchCollab today:

Faheem Ullah

26,494 次观看 • 7 个月前

arXiv Papers → LLM Artifacts This is how I keep up with AI research now. It's like having access to the most personalized arXiv feed. Automations run everyday to curate papers based a set of rules and insights. Curated papers are indexed and power the artifacts. Agent convert papers to LLM wikis (based on Andrej Karpathy idea), which means insights are indexed and easily searchable and reusable. I feel like LLM Artifacts is the natural evolution to LLM Wikis. It's about making that knowledge actionable. Artifacts are customizable via agents. Artifacts can interact with agents and are dynamic in nature. Anything can be injected into the artifact as needed (insights, components, suggested experiments, action items, etc). I can take action on Artifact items with my agent orchestrator (Electron app). So I can ask questions about any paper and automate experiments in the background right from within the artifact. This is more than a visual. It's not a single prompt. It's several proactive agents coordinating to surface interesting facts, knowledge, and insights that I can act on a researcher. Agents are not just for generating useful artifacts, they are useful to keep learning and staying on the cutting edge of knowledge. Stay tuned for more.

arXiv Papers → LLM Artifacts This is how I keep up with AI research now. It's like having access to the most personalized arXiv feed. Automations run everyday to curate papers based a set of rules and insights. Curated papers are indexed and power the artifacts. Agent convert papers to LLM wikis (based on Andrej Karpathy idea), which means insights are indexed and easily searchable and reusable. I feel like LLM Artifacts is the natural evolution to LLM Wikis. It's about making that knowledge actionable. Artifacts are customizable via agents. Artifacts can interact with agents and are dynamic in nature. Anything can be injected into the artifact as needed (insights, components, suggested experiments, action items, etc). I can take action on Artifact items with my agent orchestrator (Electron app). So I can ask questions about any paper and automate experiments in the background right from within the artifact. This is more than a visual. It's not a single prompt. It's several proactive agents coordinating to surface interesting facts, knowledge, and insights that I can act on a researcher. Agents are not just for generating useful artifacts, they are useful to keep learning and staying on the cutting edge of knowledge. Stay tuned for more.

elvis

59,177 次观看 • 4 个月前

Everyone keeps asking me how to build a second brain or an LLM wiki. Here is the easiest setup I have found. I took my Wiki Builder skill, installed it into HyperAgent (Hyperagent) as a reusable skill, and asked it to build a research wiki on LLM verification from the latest 2026 papers. Recorded a quick demo. Built with Hyperagent. It planned first, asked a few sharp questions, then did the research: 29 papers curated into 21 files, a research map, a glossary, and clean subfields. Now it is a knowledge base that my other research agents build on. HyperAgent has all the capabilities to allow your agents and skills to compound. That’s a powerful use of AI agents.

Everyone keeps asking me how to build a second brain or an LLM wiki. Here is the easiest setup I have found. I took my Wiki Builder skill, installed it into HyperAgent (Hyperagent) as a reusable skill, and asked it to build a research wiki on LLM verification from the latest 2026 papers. Recorded a quick demo. Built with Hyperagent. It planned first, asked a few sharp questions, then did the research: 29 papers curated into 21 files, a research map, a glossary, and clean subfields. Now it is a knowledge base that my other research agents build on. HyperAgent has all the capabilities to allow your agents and skills to compound. That’s a powerful use of AI agents.

elvis

226,001 次观看 • 2 个月前

My friend applied to 200 tech jobs in two years. No PhD. No Stanford. Last month Anthropic offered him $750,000. I asked him how he broke in from zero. He sent me a course that was never supposed to get out. A 3-hour video to build a full LLM from scratch. A developer teaches you exactly how LLMs like ChatGPT and Claude are actually built. I watched it last night. Halfway through, I realized it's embarrassingly simple to break into an AI lab. Bookmark this and read the article below. • 00:00 - intro to LLMs • 05:43 - LLM transformer architecture • 40:24 - training the LLM • 1:30:27 - modernizing the LLM • 2:33:53 - scaling the LLM

My friend applied to 200 tech jobs in two years. No PhD. No Stanford. Last month Anthropic offered him $750,000. I asked him how he broke in from zero. He sent me a course that was never supposed to get out. A 3-hour video to build a full LLM from scratch. A developer teaches you exactly how LLMs like ChatGPT and Claude are actually built. I watched it last night. Halfway through, I realized it's embarrassingly simple to break into an AI lab. Bookmark this and read the article below. • 00:00 - intro to LLMs • 05:43 - LLM transformer architecture • 40:24 - training the LLM • 1:30:27 - modernizing the LLM • 2:33:53 - scaling the LLM

Roan

279,295 次观看 • 2 个月前

Consensus in an AI-powered search engine that answers your questions with reference to published papers. No hallucinations. No fake citations to papers that don't exist. Here is a new Consensus feature that will make your literature review faster and easier. Ask a question and Consensus will give you a list of relevant papers. You can filter papers by: • Year • Study Type (Meta Analysis, Literature Review, Systematic Review, Case Report, etc.) • Study Details (Controlled Study, Human Study, Sample Size) Here I am asking a question about how people self manage lower back pain. I am filtering papers so I only see meta analyses and systematic reviews published in 2020.

Consensus in an AI-powered search engine that answers your questions with reference to published papers. No hallucinations. No fake citations to papers that don't exist. Here is a new Consensus feature that will make your literature review faster and easier. Ask a question and Consensus will give you a list of relevant papers. You can filter papers by: • Year • Study Type (Meta Analysis, Literature Review, Systematic Review, Case Report, etc.) • Study Details (Controlled Study, Human Study, Sample Size) Here I am asking a question about how people self manage lower back pain. I am filtering papers so I only see meta analyses and systematic reviews published in 2020.

Mushtaq Bilal, PhD

115,771 次观看 • 3 年前

Last week, I received reviews from a journal. 2 of the 3 reviewers pointed out the same issue. 𝑇ℎ𝑒 𝑓𝑜𝑙𝑙𝑜𝑤𝑖𝑛𝑔 𝑝𝑎𝑝𝑒𝑟 𝑖𝑠 𝑚𝑖𝑠𝑠𝑖𝑛𝑔 𝑓𝑟𝑜𝑚 𝑡ℎ𝑒 𝑙𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑟𝑒𝑣𝑖𝑒𝑤. Upon checking, I realized the paper was very relevant. I was surprised how I missed this paper. I re-run the search terms on Google Scholar. The identified paper still went missing. Then I tried searching using ResearchRabbit ResearchRabbit picked the paper. 𝐇𝐞𝐫𝐞 𝐢𝐬 𝐡𝐨𝐰 𝐈 𝐮𝐬𝐞𝐝 𝐑𝐞𝐬𝐞𝐚𝐫𝐜𝐡𝐑𝐚𝐛𝐛𝐢𝐭. 1. I logged into 2. I searched 2-3 papers I already knew 3. ResearchRabbit built a visual map of related papers. 4. Then I explored the map → x-axis shows the publication date → y-axis shows the citation count 5. On each paper in map, I clicked “𝑓𝑖𝑛𝑑 𝑟𝑒𝑙𝑎𝑡𝑒𝑑 𝑝𝑎𝑝𝑒𝑟” 6. This way, each paper becomes a seed 7. With each round, I identified more papers. This way I identified papers that I totally missed before. I saved the papers within the library. I also included the missing papers in my review. You don’t want to miss any relevant papers? Try ResearchRabbit:

Last week, I received reviews from a journal. 2 of the 3 reviewers pointed out the same issue. 𝑇ℎ𝑒 𝑓𝑜𝑙𝑙𝑜𝑤𝑖𝑛𝑔 𝑝𝑎𝑝𝑒𝑟 𝑖𝑠 𝑚𝑖𝑠𝑠𝑖𝑛𝑔 𝑓𝑟𝑜𝑚 𝑡ℎ𝑒 𝑙𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑟𝑒𝑣𝑖𝑒𝑤. Upon checking, I realized the paper was very relevant. I was surprised how I missed this paper. I re-run the search terms on Google Scholar. The identified paper still went missing. Then I tried searching using ResearchRabbit ResearchRabbit picked the paper. 𝐇𝐞𝐫𝐞 𝐢𝐬 𝐡𝐨𝐰 𝐈 𝐮𝐬𝐞𝐝 𝐑𝐞𝐬𝐞𝐚𝐫𝐜𝐡𝐑𝐚𝐛𝐛𝐢𝐭. 1. I logged into 2. I searched 2-3 papers I already knew 3. ResearchRabbit built a visual map of related papers. 4. Then I explored the map → x-axis shows the publication date → y-axis shows the citation count 5. On each paper in map, I clicked “𝑓𝑖𝑛𝑑 𝑟𝑒𝑙𝑎𝑡𝑒𝑑 𝑝𝑎𝑝𝑒𝑟” 6. This way, each paper becomes a seed 7. With each round, I identified more papers. This way I identified papers that I totally missed before. I saved the papers within the library. I also included the missing papers in my review. You don’t want to miss any relevant papers? Try ResearchRabbit:

Faheem Ullah

17,012 次观看 • 8 个月前

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

AK

83,681 次观看 • 3 年前

Today, I am launching Paper Breakdown. - PBD gets you academic paper recommendations and lets you study CS/ML/AI research with LLM agents. - It highlights relevant sections directly in the actual PDF - generates flowcharts/illustrations too - we provide an in-build screenshot tool to send images to the agent directly from the paper. - we also got agentic paper search that allows you to search our database of 70,000+ CS and ML Arxiv papers in seconds using natural language. I have been building PBD for almost half a year - it all started as a means for me to keep up with research and use AI to produce visuals and scripts for my own YouTube videos. I have developed it enough to confidently recommend it to you. Visit our landing page to learn more.

Today, I am launching Paper Breakdown. - PBD gets you academic paper recommendations and lets you study CS/ML/AI research with LLM agents. - It highlights relevant sections directly in the actual PDF - generates flowcharts/illustrations too - we provide an in-build screenshot tool to send images to the agent directly from the paper. - we also got agentic paper search that allows you to search our database of 70,000+ CS and ML Arxiv papers in seconds using natural language. I have been building PBD for almost half a year - it all started as a means for me to keep up with research and use AI to produce visuals and scripts for my own YouTube videos. I have developed it enough to confidently recommend it to you. Visit our landing page to learn more.

AVB

14,579 次观看 • 8 个月前

New short course on Building Applications with Vector Databases, taught by Pinecone’s Tim Tully! At the heart of a vector database is the ability to store a collection of vectors and then query against that, meaning input a new vector and find similar ones. This is useful for many AI applications. In this course, you'll learn how to use vector databases to build: (i) Semantic Search: Create a text search tool that goes beyond keyword matching, and instead focuses on the meaning of content. (ii) RAG (retrieval augmented generation): Enhance your LLM output by incorporating context from sources the model wasn't trained on. (iii) Recommender System: Combine semantic search and RAG to recommend topics, and demonstrate it with a news article recommender. (iv) Hybrid Search: Build an application that finds items using both images and descriptive text -- by combining both sparse and dense vector representations of the data -- using an eCommerce dataset as an example. (v) Image Similarity: Use image vector embeddings to create an app to compare facial features, using a database of public figures to determine the likeness between them. (vi) Anomaly Detection: Build an anomaly detection app that identifies unusual patterns in network communication logs. I hope you’ll enjoy learning how to build all these types of applications! Please sign up here:

New short course on Building Applications with Vector Databases, taught by Pinecone’s Tim Tully! At the heart of a vector database is the ability to store a collection of vectors and then query against that, meaning input a new vector and find similar ones. This is useful for many AI applications. In this course, you'll learn how to use vector databases to build: (i) Semantic Search: Create a text search tool that goes beyond keyword matching, and instead focuses on the meaning of content. (ii) RAG (retrieval augmented generation): Enhance your LLM output by incorporating context from sources the model wasn't trained on. (iii) Recommender System: Combine semantic search and RAG to recommend topics, and demonstrate it with a news article recommender. (iv) Hybrid Search: Build an application that finds items using both images and descriptive text -- by combining both sparse and dense vector representations of the data -- using an eCommerce dataset as an example. (v) Image Similarity: Use image vector embeddings to create an app to compare facial features, using a database of public figures to determine the likeness between them. (vi) Anomaly Detection: Build an anomaly detection app that identifies unusual patterns in network communication logs. I hope you’ll enjoy learning how to build all these types of applications! Please sign up here:

Andrew Ng

137,169 次观看 • 2 年前

How to compare 10 papers in 10 seconds? Meet 𝐒𝐜𝐢𝐒𝐩𝐚𝐜𝐞 – this tool compares papers for you. Here is how it works. 1. Go to 2. Click on + 𝑠𝑖𝑔𝑛 and upload the 10 papers. 3. After uploading papers, write your prompt. 𝐶𝑜𝑚𝑝𝑎𝑟𝑒 𝑡ℎ𝑒 𝑢𝑝𝑙𝑜𝑎𝑑𝑒𝑑 10 𝑟𝑒𝑠𝑒𝑎𝑟𝑐ℎ 𝑝𝑎𝑝𝑒𝑟𝑠 4. SciSpace will start comparing the papers. 5. You will see the comparison result on right side. 6. You will see various insights with paper numbers. 7. At the end, you will see summary of the comparison. 8. SciSpace compares the papers based on: ✓ Similarities in research themes ✓ Differences in approaches ✓ Relative strengths and weaknesses ✓ Gaps identified across papers ✓ Relationships and building upon each other 9. To trace to each paper, click on the 𝑝𝑎𝑝𝑒𝑟 𝑛𝑢𝑚𝑏𝑒𝑟𝑠 10. To trace to exact location, click on 𝑙𝑜𝑐𝑎𝑡𝑒 𝑃𝐷𝐹. Where can you use such comparison? You can use it to: ➝ Understand the related literature. ➝ Position the novelty of your research paper. ➝ Understand niche questions in a research area. ➝ Grasp key insights from a bunch of papers in one go. Try SciSpace today:

How to compare 10 papers in 10 seconds? Meet 𝐒𝐜𝐢𝐒𝐩𝐚𝐜𝐞 – this tool compares papers for you. Here is how it works. 1. Go to 2. Click on + 𝑠𝑖𝑔𝑛 and upload the 10 papers. 3. After uploading papers, write your prompt. 𝐶𝑜𝑚𝑝𝑎𝑟𝑒 𝑡ℎ𝑒 𝑢𝑝𝑙𝑜𝑎𝑑𝑒𝑑 10 𝑟𝑒𝑠𝑒𝑎𝑟𝑐ℎ 𝑝𝑎𝑝𝑒𝑟𝑠 4. SciSpace will start comparing the papers. 5. You will see the comparison result on right side. 6. You will see various insights with paper numbers. 7. At the end, you will see summary of the comparison. 8. SciSpace compares the papers based on: ✓ Similarities in research themes ✓ Differences in approaches ✓ Relative strengths and weaknesses ✓ Gaps identified across papers ✓ Relationships and building upon each other 9. To trace to each paper, click on the 𝑝𝑎𝑝𝑒𝑟 𝑛𝑢𝑚𝑏𝑒𝑟𝑠 10. To trace to exact location, click on 𝑙𝑜𝑐𝑎𝑡𝑒 𝑃𝐷𝐹. Where can you use such comparison? You can use it to: ➝ Understand the related literature. ➝ Position the novelty of your research paper. ➝ Understand niche questions in a research area. ➝ Grasp key insights from a bunch of papers in one go. Try SciSpace today:

Faheem Ullah

24,341 次观看 • 7 个月前

One AI skill that changes how you read academic papers. It turns every reference into a reusable writing block. I call this method: Atomic sentences. Atomic sentence = One sentence. One claim. One source. You can extract them directly from a peer-reviewed paper, vetted by authors and reviewers before it ever reaches you. It is a form of summarising the content, but the output can be reused and recombined in your writing. Here's how it works 👇 1. Upload any paper to Claude and trigger the /ea-atomic-sentences skill. It breaks down every cited reference into a single compressed claim. (Repeat on as many papers as needed) 2. Pick 5–6 sentences relevant to an argument and arrange them coherently, so it makes sense. Add your own ideas/findings as well. 3. Ask Claude to combine them into a coherent paragraph. What you get is surprisingly well-written paragraphs. Use the skill /ea-academic-writer for even better results. ✅ Every reference in that paragraph is real. ✅ Every claim was made by a human researcher. ✅ You control the narrative of what is being said in your paper, but build on the findings of others. Disclaimer: Don't skip reading, as you need to understand your domain to use this and don't rely 100% on AI, as it can make mistakes.

One AI skill that changes how you read academic papers. It turns every reference into a reusable writing block. I call this method: Atomic sentences. Atomic sentence = One sentence. One claim. One source. You can extract them directly from a peer-reviewed paper, vetted by authors and reviewers before it ever reaches you. It is a form of summarising the content, but the output can be reused and recombined in your writing. Here's how it works 👇 1. Upload any paper to Claude and trigger the /ea-atomic-sentences skill. It breaks down every cited reference into a single compressed claim. (Repeat on as many papers as needed) 2. Pick 5–6 sentences relevant to an argument and arrange them coherently, so it makes sense. Add your own ideas/findings as well. 3. Ask Claude to combine them into a coherent paragraph. What you get is surprisingly well-written paragraphs. Use the skill /ea-academic-writer for even better results. ✅ Every reference in that paragraph is real. ✅ Every claim was made by a human researcher. ✅ You control the narrative of what is being said in your paper, but build on the findings of others. Disclaimer: Don't skip reading, as you need to understand your domain to use this and don't rely 100% on AI, as it can make mistakes.

Ilya Shabanov

16,186 次观看 • 4 个月前

Millions of users scroll through endless transaction feeds trying to answer simple questions about their money. That’s why we built Conversational Transaction Insights directly into PhonePe. When building Conversational Transaction Insights for PhonePe, we wanted to eliminate the friction of digging through statements or tweaking filters. You should be able to ask a spending question in plain language via text or voice and get an accurate answer instantly. The core engineering challenge wasn't just wrapping an LLM around data - it was combining natural language flexibility with deterministic analytical precision and uncompromising user privacy. Whether tracking food expenses over the last 6 months or analyzing utility trends, financial clarity is now just a quick conversation / text away. Here’s a look at how it works!

Millions of users scroll through endless transaction feeds trying to answer simple questions about their money. That’s why we built Conversational Transaction Insights directly into PhonePe. When building Conversational Transaction Insights for PhonePe, we wanted to eliminate the friction of digging through statements or tweaking filters. You should be able to ask a spending question in plain language via text or voice and get an accurate answer instantly. The core engineering challenge wasn't just wrapping an LLM around data - it was combining natural language flexibility with deterministic analytical precision and uncompromising user privacy. Whether tracking food expenses over the last 6 months or analyzing utility trends, financial clarity is now just a quick conversation / text away. Here’s a look at how it works!

Rahul Chari

15,355 次观看 • 1 个月前

New short course on LLMOps! LLMOps (large language model operations) is a rapidly developing field that takes ideas from MLOps (machine learning operations) and specializes them to building and deploying LLM-based applications. In this course, taught by Google Cloud's Erwin Huizenga, you'll learn to use automation to make building, tuning and deploying an LLM-based application less manual and more efficient. You'll learn how to: - Apply supervised fine-tuning to tune an LLM to a specific task - Automate and orchestrate LLM-tuning and deployment by customizing a pre-built tuning pipeline - Apply best practices for preparing training data for supervised fine-tuning of an LLM - Create an LLMOps workflow you can adapt to other LLM-tuning jobs This course doesn't assume any prior MLOps or LLMOps experience. Sign up here to learn about this emerging field!

New short course on LLMOps! LLMOps (large language model operations) is a rapidly developing field that takes ideas from MLOps (machine learning operations) and specializes them to building and deploying LLM-based applications. In this course, taught by Google Cloud's Erwin Huizenga, you'll learn to use automation to make building, tuning and deploying an LLM-based application less manual and more efficient. You'll learn how to: - Apply supervised fine-tuning to tune an LLM to a specific task - Automate and orchestrate LLM-tuning and deployment by customizing a pre-built tuning pipeline - Apply best practices for preparing training data for supervised fine-tuning of an LLM - Create an LLMOps workflow you can adapt to other LLM-tuning jobs This course doesn't assume any prior MLOps or LLMOps experience. Sign up here to learn about this emerging field!

Andrew Ng

221,803 次观看 • 2 年前

I remember writing and designing a short story with plain A4 papers, markers and a very beautiful stamp when I was about 7/8 years old. I wanted even then to be an author, I was reading books voraciously and I wanted to create mine too. 1/5

I remember writing and designing a short story with plain A4 papers, markers and a very beautiful stamp when I was about 7/8 years old. I wanted even then to be an author, I was reading books voraciously and I wanted to create mine too. 1/5

Oluwaremilekun

21,263 次观看 • 10 个月前