正在加载视频...

视频加载失败

返回首页

Introducing `claude-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source.

mattshumer_'s profile picture

Matt Shumer

372,624 subscribers

383,165 次观看 • 2 年前 •via X (Twitter)

教育喜剧科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

9 条评论

Matt Shumer 的头像
Matt Shumer2 年前

How it works: - The user describes the model they want Ex: "A model that writes Python functions" - claude-llm-trainer leverages a chain of Claude 3 calls to create a great dataset for your task. - We process the dataset, and train a LLaMA model!

Matt Shumer 的头像
Matt Shumer2 年前

This was based off of an older project I did, so the model we train is LLaMA 2 7B. If you want, you can easily use a newer + better model like Mistral 7B.

Matt Shumer 的头像
Matt Shumer2 年前

You can go from an idea to a fully trained model in a matter of minutes. And the resulting models are really capable!

Matt Shumer 的头像
Matt Shumer2 年前

If you'd like to try it or contribute, check out the Github repo:

Matt Shumer 的头像
Matt Shumer2 年前

Incredible haha

mAI 的头像
mAI2 年前

Man, do you ever sleep?

Matt Shumer 的头像
Matt Shumer2 年前

Haha yeah, been getting this question a lot lately though lol

AI Adventurer 的头像
AI Adventurer2 年前

Well, that sir is excellent stuff!

al𝕏 的头像
al𝕏2 年前

LLM recursion 😂 that's awesome

相关视频

Introducing `gpt-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. **Just write a sentence describing the model you want.** A chain of AI systems will generate a dataset and train a model for you. And it's open-source:
1:01

Introducing `gpt-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. **Just write a sentence describing the model you want.** A chain of AI systems will generate a dataset and train a model for you. And it's open-source:

Matt Shumer

337,433 次观看 • 3 年前

Introducing `AutoRL` 📈 The world's simplest way to train a task-specific LLM with RL. *Just write a SENTENCE describing the model you want.* A chain of AI systems will generate data + rubrics and train a model for you. Powered by ART, it's open source. Link in thread:
0:47

Introducing `AutoRL` 📈 The world's simplest way to train a task-specific LLM with RL. *Just write a SENTENCE describing the model you want.* A chain of AI systems will generate data + rubrics and train a model for you. Powered by ART, it's open source. Link in thread:

Matt Shumer

150,107 次观看 • 1 年前

Introducing `claude-prompt-engineer` ✍️ An agent that creates optimal Claude 3 prompts. Just describe a task, and a chain of AIs will: - Generate many possible prompts - Test them in a ranked tournament - Return the best one And it's open-source:
0:41

Introducing `claude-prompt-engineer` ✍️ An agent that creates optimal Claude 3 prompts. Just describe a task, and a chain of AIs will: - Generate many possible prompts - Test them in a ranked tournament - Return the best one And it's open-source:

Matt Shumer

767,219 次观看 • 2 年前

Introducing `Claude-Author` 📕✍️ One prompt -> an entire novel! Just describe the high-level details, and a chain of AI systems will write an entire book for you in minutes. - complete w/ cover art - packages your book as a real e-book And it's open-source!
0:44

Introducing `Claude-Author` 📕✍️ One prompt -> an entire novel! Just describe the high-level details, and a chain of AI systems will write an entire book for you in minutes. - complete w/ cover art - packages your book as a real e-book And it's open-source!

Matt Shumer

671,966 次观看 • 2 年前

Introducing `gpt-author v2` 📕✍️ One prompt -> an entire fantasy novel! Just describe the high-level details, and a chain of AI systems will write an entire book for you in minutes. - complete w/ cover art - export to ebook format And it's open-source:
0:52

Introducing `gpt-author v2` 📕✍️ One prompt -> an entire fantasy novel! Just describe the high-level details, and a chain of AI systems will write an entire book for you in minutes. - complete w/ cover art - export to ebook format And it's open-source:

Matt Shumer

276,531 次观看 • 2 年前

Introducing `gpt-author` 📕✍️ One prompt -> an entire fantasy novel! Just describe the high-level details, and a chain of AI systems will write an entire book for you in minutes. - complete w/ cover art - export to Kindle store And it's open-source:
0:24

Introducing `gpt-author` 📕✍️ One prompt -> an entire fantasy novel! Just describe the high-level details, and a chain of AI systems will write an entire book for you in minutes. - complete w/ cover art - export to Kindle store And it's open-source:

Matt Shumer

2,101,780 次观看 • 3 年前

Introducing `claude-researcher` 📈 A powerful Claude 3 research agent that delivers thorough reports in record time. Just provide an topic, and a chain of AIs with **access to Google** will generate an incredibly comprehensive report for you. And it's open-source!
0:37

Introducing `claude-researcher` 📈 A powerful Claude 3 research agent that delivers thorough reports in record time. Just provide an topic, and a chain of AIs with **access to Google** will generate an incredibly comprehensive report for you. And it's open-source!

Matt Shumer

397,549 次观看 • 2 年前

Introducing `claude-opus-to-haiku` ✍️ Get the quality of Claude 3 Opus, at a fraction of the cost and latency. Give one example of your task, and Claude 3 Opus will teach Haiku (60x cheaper!!) how to do the task perfectly. And it's open-source:
0:25

Introducing `claude-opus-to-haiku` ✍️ Get the quality of Claude 3 Opus, at a fraction of the cost and latency. Give one example of your task, and Claude 3 Opus will teach Haiku (60x cheaper!!) how to do the task perfectly. And it's open-source:

Matt Shumer

285,428 次观看 • 2 年前

Groq is the world's fastest LLM (Large Language Model). Faster than ChatGPT, Claude, and Google Gemini. And you can use it for free! Here's Groq answering a megaprompt of 300+ words instantly. In less than a second, it created a preliminary outline for a journal article and a writing schedule. It's unbelievable!
0:34

Groq is the world's fastest LLM (Large Language Model). Faster than ChatGPT, Claude, and Google Gemini. And you can use it for free! Here's Groq answering a megaprompt of 300+ words instantly. In less than a second, it created a preliminary outline for a journal article and a writing schedule. It's unbelievable!

Mushtaq Bilal, PhD

162,550 次观看 • 2 年前

LLMOps, a new course with @GoogleCloud is available now. Learn Large Language Model Operations (LLMOps) best practices as you design and automate the steps to tune an LLM for a specific task and deploy it as a callable API. Learn more and enroll now:
2:11

LLMOps, a new course with @GoogleCloud is available now. Learn Large Language Model Operations (LLMOps) best practices as you design and automate the steps to tune an LLM for a specific task and deploy it as a callable API. Learn more and enroll now:

DeepLearning.AI

33,717 次观看 • 2 年前

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.
2:52

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 次观看 • 2 年前

New course: Build and Train an LLM with JAX, built in partnership with Google and taught by Chris Achard. JAX is the open-source library behind Google's Gemini, Veo, and other advanced models. This short course teaches you to build and train a 20-million parameter language model from scratch using JAX and its ecosystem of tools. You'll implement a complete MiniGPT-style architecture from scratch, train it, and chat with your finished model through a graphical interface. Skills you'll gain: - Learn JAX's core primitives: automatic differentiation, JIT compilation, and vectorized execution - Build a MiniGPT-style LLM using Flax/NNX, implementing embedding and transformer blocks - Load a pretrained MiniGPT model and run inference through a chat interface Come learn this important software layer for building LLMs!
1:54

New course: Build and Train an LLM with JAX, built in partnership with Google and taught by Chris Achard. JAX is the open-source library behind Google's Gemini, Veo, and other advanced models. This short course teaches you to build and train a 20-million parameter language model from scratch using JAX and its ecosystem of tools. You'll implement a complete MiniGPT-style architecture from scratch, train it, and chat with your finished model through a graphical interface. Skills you'll gain: - Learn JAX's core primitives: automatic differentiation, JIT compilation, and vectorized execution - Build a MiniGPT-style LLM using Flax/NNX, implementing embedding and transformer blocks - Load a pretrained MiniGPT model and run inference through a chat interface Come learn this important software layer for building LLMs!

Andrew Ng

192,696 次观看 • 5 个月前

this guy got tired of going back and forth with Claude Code describing what's wrong with the UI so he built a tool that lets you DRAW DIRECTLY on the screen claude renders something. if it's wrong you just circle the problem, add an arrow, write a note ai sees your annotations and fixes it way faster than describing it by text AND it's free + open source
0:33

this guy got tired of going back and forth with Claude Code describing what's wrong with the UI so he built a tool that lets you DRAW DIRECTLY on the screen claude renders something. if it's wrong you just circle the problem, add an arrow, write a note ai sees your annotations and fixes it way faster than describing it by text AND it's free + open source

Om Patel

108,733 次观看 • 4 个月前

Introducing CADGenBench: measure how well AI systems produce engineering-grade 3D parts! While current models can generate 3D parts, they are far from precise enough to build functional parts. We built a benchmark to systematically measure their capabilities on two tasks: 1. Generation from an engineering drawing of a part 2. Editing: given an existing STEP file and a requested change The benchmark is tool-agnostic. It makes no assumptions about how you build the model. You can vary the LLM, and you can vary the environment. Use build123d, Onshape, Autodesk, or a model without an LLM entirely. We open sourced the scoring engine and a reference baseline on top of build123d. A collaboration between Hugging Face and Mecado! Submission space: Code repository:
0:43

Introducing CADGenBench: measure how well AI systems produce engineering-grade 3D parts! While current models can generate 3D parts, they are far from precise enough to build functional parts. We built a benchmark to systematically measure their capabilities on two tasks: 1. Generation from an engineering drawing of a part 2. Editing: given an existing STEP file and a requested change The benchmark is tool-agnostic. It makes no assumptions about how you build the model. You can vary the LLM, and you can vary the environment. Use build123d, Onshape, Autodesk, or a model without an LLM entirely. We open sourced the scoring engine and a reference baseline on top of build123d. A collaboration between Hugging Face and Mecado! Submission space: Code repository:

Michael Rabinovich

64,344 次观看 • 1 个月前

In just two weeks: some of the largest supply-chain attacks in history, a major commercial LLM sabotaging legitimate ML research requests, and a US export ban kneecapping the world's access to a major model release. More than ever, we need Open, Verifiable Inference. Today we start shipping direct responses. A🧵:
1:18

In just two weeks: some of the largest supply-chain attacks in history, a major commercial LLM sabotaging legitimate ML research requests, and a US export ban kneecapping the world's access to a major model release. More than ever, we need Open, Verifiable Inference. Today we start shipping direct responses. A🧵:

ambient.xyz

53,505 次观看 • 1 个月前

this is why open-source wins every time.. open weights allow you to invent new model capabilities, train + generate locally (crucial for NDA'd and personal data), push the limits of what's currently possible + lean into a huge community of experts for advice and inspiration 🖤
2:35

this is why open-source wins every time.. open weights allow you to invent new model capabilities, train + generate locally (crucial for NDA'd and personal data), push the limits of what's currently possible + lean into a huge community of experts for advice and inspiration 🖤

Ingi Erlingsson 🪄

16,877 次观看 • 2 个月前

📢 New short course in collaboration with Google: Build and Train an LLM with JAX. In this course, you’ll implement and train a 20M-parameter MiniGPT-style language model from scratch using JAX, the open-source library behind Gemini. You’ll build the model architecture, load and preprocess training data, implement the training loop, save checkpoints, and generate text through a chat interface. Taught by Chris Achard, Developer Relations Engineer on Google’s TPU Software team. Enroll now:
1:54

📢 New short course in collaboration with Google: Build and Train an LLM with JAX. In this course, you’ll implement and train a 20M-parameter MiniGPT-style language model from scratch using JAX, the open-source library behind Gemini. You’ll build the model architecture, load and preprocess training data, implement the training loop, save checkpoints, and generate text through a chat interface. Taught by Chris Achard, Developer Relations Engineer on Google’s TPU Software team. Enroll now:

DeepLearning.AI

46,065 次观看 • 5 个月前

Most "agentic" failures happen because the model lacks specific domain knowledge. Here I'm showing how loading a Skills Plugin solves that for dataset generation. I turned a research paper (shows fine-tuning dataset creation from books) into a Skill and just gave a book link and asked it to generate the dataset. Claude Code produced a clean SFT-ready dataset from a single URL. The same process can be applied to anything.
0:58

Most "agentic" failures happen because the model lacks specific domain knowledge. Here I'm showing how loading a Skills Plugin solves that for dataset generation. I turned a research paper (shows fine-tuning dataset creation from books) into a Skill and just gave a book link and asked it to generate the dataset. Claude Code produced a clean SFT-ready dataset from a single URL. The same process can be applied to anything.

Muratcan Koylan

104,519 次观看 • 7 个月前