Train an LLM to Self-Correct with Verifiable Backtracking

Автор: Trelis Research

Загружено: 2025-02-20

Просмотров: 4794

Описание:

📜Get repo access at Trelis.com/ADVANCED-fine-tuning

Tip: If you subscribe here on YouTube, click the bell to be notified of new vids

🛠 Build & Deploy Faster
Fine-tuning, Inference, Audio, Evals, and Vision Tools: https://trelis.com

💡 Need Technical or Market Assistance?
Book a Consult Here: https://forms.gle/wJXVZXwioKMktjyVA

🤝 Are You a Top Developer?
Join the Trelis team: https://trelis.com/developer-collabor...

💸 Starting a New Project/Venture?
Apply for a Trelis Grant: https://trelis.com/trelis-ai-grants/

📧 Get Trelis AI Tutorials by Email
Subscribe on Substack: https://trelis.substack.com

📸 Thumbnail Tutorial
See How It’s Made: • Fine Tune Flux Diffusion Models with Your ...

Video Links:
s1 paper: https://arxiv.org/pdf/2501.19393

TIMESTAMPS:
00:00 Introduction to Verifiable Backtracking
00:45 Understanding Backtracking in LLMs
01:55 Budget Forcing Technique
06:01 Verifiable Backtracking Explained
10:49 Implementing Verifiable Backtracking in Code
17:39 Evaluating the Performance
22:43 Conclusion and Final Thoughts

Train an LLM to Self-Correct with Verifiable Backtracking

Доступные форматы для скачивания:

Скачать видео mp4

Информация по загрузке:

Скачать аудио mp3

Похожие видео

SFT vs GRPO

How does GRPO work?

How does GRPO work?

Train an LLM from Scratch with Karpathy's Nanochat

Train an LLM from Scratch with Karpathy's Nanochat

GhostWriter AI: The Agentic System That Writes ALL Your Content for You #agenticai

GhostWriter AI: The Agentic System That Writes ALL Your Content for You #agenticai

QLoRA—How to Fine-tune an LLM on a Single GPU (w/ Python Code)

QLoRA—How to Fine-tune an LLM on a Single GPU (w/ Python Code)

Что я думаю про будущее разработки в эпоху ИИ

Что я думаю про будущее разработки в эпоху ИИ

Test-Time Compute and Test-Time Training TTT

Test-Time Compute and Test-Time Training TTT

Which Quantization Method is Right for You? (GPTQ vs. GGUF vs. AWQ)

Which Quantization Method is Right for You? (GPTQ vs. GGUF vs. AWQ)

Отъём жилья. Не только Долина. Статус S09E15

Отъём жилья. Не только Долина. Статус S09E15

I Trained an LLM to Think Deeper (Here's How)

I Trained an LLM to Think Deeper (Here's How)

Train Your Own Reasoning Model (DeepSeek Clone) Fast & With Only 7Gb Of VRAM

Train Your Own Reasoning Model (DeepSeek Clone) Fast & With Only 7Gb Of VRAM

Как ИИ сломает твой ДНК и почему ТЕБЕ ЭТО ПОНРАВИТСЯ

Как ИИ сломает твой ДНК и почему ТЕБЕ ЭТО ПОНРАВИТСЯ

ДНК создал Бог? Самые свежие научные данные о строении. Как работает информация для жизни организмов

ДНК создал Бог? Самые свежие научные данные о строении. Как работает информация для жизни организмов

Training LLM to play chess using Deepseek GRPO reinforcement learning

Training LLM to play chess using Deepseek GRPO reinforcement learning

Fine-tuning Llama 3.2 on Your Data with a single GPU | Training LLM for Sentiment Analysis

Fine-tuning Llama 3.2 on Your Data with a single GPU | Training LLM for Sentiment Analysis

Tülu 3 from AI2: Full open-source fine-tuning recipe for LLMs

Tülu 3 from AI2: Full open-source fine-tuning recipe for LLMs

Train A DeepSeek Style Reasoning Model With UnslothAI (Local Tutorial)

Train A DeepSeek Style Reasoning Model With UnslothAI (Local Tutorial)

How does DeepSeek learn? GRPO explained with Triangle Creatures

How does DeepSeek learn? GRPO explained with Triangle Creatures

Объяснение тензорных процессоров (TPU)

Объяснение тензорных процессоров (TPU)

Combined Preference and Supervised Fine Tuning with ORPO

Combined Preference and Supervised Fine Tuning with ORPO