Curriculum
1. Is Vicuna the ChatGPT Killer?
2. ChatGPT for YOUR OWN PDF files with LangChain
3. AUTO-GPT: Autonomous GPT-4! Mini AGI is HERE!
4. GPT 4 Can NOW Self Reflect Just Like Humans!
5. Open Assistant: Open Source ChatGPT is Here!!! [live Demo]
6. UNCENSORED GPT4 x Alpaca & Vicuna [Local Install + Tutorial]
7. Koala: Relatively Uncensored Vicuna/ChatGPT Alternative [Tutorial]
8. 🤯 Spark of AGI? 🤯 AI Agents Behaving Like Humans
9. Working with MULTIPLE PDF Files in LangChain: ChatGPT for your Data
10. HUGE GPT4ALL Upgrade, CPU, Commercial License, 1-Click Install, New UI, New Base Model
11. DataBricks Dolly 2.0, Commercial Use, TRUE Open Source LLM
12. LangChain Crash Course - All You Need to Know to Build Powerful Apps with LLMs
13. Test AutoGPT for FREE & Other Cool Open Source Projects
14. Talk to YOUR DATA without OpenAI APIs: LangChain
15. RedPajama - Llama is getting Open Source!
16. MiniGPT4: Open Source GPT-4 with VISION
17. StableLM: Small BUT Mighty LLM | Open Source & Commerical Use
18. NVIDIA's NEW INSANE "TEXT To Video" AI
19. LLaVA: Now You can Chat with Your Images | GPT-4 is Supposed to have This
20. LangChain: Run Language Models Locally - Hugging Face Models
21. HuggingChat: This is HUGE for Open Source ChatGPT!
22. WizardLM: The Best 7B LLM - Can Beat ChatGPT
23. Stable-Vicuna: The Most Powerful Open-Source LLM Yet?
24. Llama is Finally OPEN - Commercial Use is Welcome!
25. Mojo 🔥— NEW Language for AI (FIRST Look)
26. Which OPEN LLM is the BEST?? (3B to 13B models)
27. Wizard-Vicuna: 97% of ChatGPT - with Oobabooga Text Generation WebUI
28. WizardLM But UNCENSORED!!!
29. BEST OPEN Alternative to OPENAI's EMBEDDINGs for Retrieval QA: LangChain
30. CHATGPT For WEBSITES: Custom ChatBOT: LangChain Tutorial
31. Claude's 100K Token Context Window is INSANE!
32. Huggingface Agents: Multimodal Transformers Agents Are Here & Its Open Source
33. PrivateGPT: Chat to your FILES OFFLINE and FREE [Installation and Tutorial]
34. Wizard Mega 13B: The NEW UNCENSORED BEST 13B LLM
35. Langchain: PDF Chat App (GUI) | ChatGPT for Your PDF FILES | Step-by-Step Tutorial
36. ⛓️ LangFlow: Build Chatbots without Writing Code - LangChain
37. Google NEW PaLM API | FIRST LOOK
38. NEW GUANACO LLM with QLoRA: As GOOD as ChatGPT!
39. FALCON LLM - NEW KING on OPEN LLM LEADERBOARD!
40. LocalGPT: OFFLINE CHAT FOR YOUR FILES [Installation & Code Walkthrough]
41. PDF Files to FLASH CARDS - Automate YOUR Learning with ChatGPT - Tutorial
42. Custom GUI App for Open-Assistant API - Tutorial | Step by step Guide
43. Flowise: No Code ChatBot Building Platform: LangChain
44. Gorilla: An API Appstore for LLMs
45. LangChain: Giving Memory to LLMs
46. Gorilla: An API Appstore for LLMs
47. NEW BEST 100% Uncensored Local LLM
48. Prompt Engineering - Get the MOST OUT of ChatGPT/GPT-4
49. ChatGPT 16K Token Context Window is INSANE!
50. GPT-ENGINEER: Build POWERFUL APPs with ONE PROMPT [Installation & Tutorial]
51. VoiceBox: Meta's NEW AI Clones Voices with only 2 Seconds of Audio!
52. NEW FalCoder-7B: The Best Open Coding Assistant? | Installation & Tutorial
53. Updated Oobabooga Textgen WebUI for M1/M2 [Installation & Tutorial]
54. NEW ORCA-Mini 🐳 Open-Sourced LLM that You can RUN Locally
55. Running MPT-30B on CPU - You DON"T Need a GPU
56. Private video
57. AIDER: NEW GPT-Engineer | AI Coding Assistant | Installation & Tutorial
58. Slash API Costs: Mastering Caching for LLM Applications
59. ChatBOT with Memory for Your Documents - OpenAI & LocalGPT
60. LongNET: WHOLE INTERNET in A SINGLE PROMPT
61. Can Claude 2 Outperform ChatGPT? Anthropic Thinks So!
62. Private video
63. Open-Orca: The FIRST Version is OUT.
64. Open-Orca: The FIRST Version is OUT - Audio Fixed :)
65. LLAMA-2 is Here - FREE FOR COMMERCIAL USE 🔥 🔥 🔥
66. Run Llama-2 Locally within Text Generation WebUI - Oobabooga
67. Fully Uncensored Llama-2 is HERE 🔥 🔥 🔥
68. Llama-2 with LocalGPT: Chat with YOUR Documents
69. FreeWilly (Orca 🐳): NEW LLM Leader! Better Than Llama-2
70. Is this Really about AI Safety??
71. Run Huge GPT Models the on Any Device with Torrent-GPT
72. Private video
73. LocalGPT & Llama-2: Adding Chat History & Custom Prompt Templates
74. LocalGPT API: Build Powerful Doc Chat Apps
75. SMALL BUT MIGHTY - 13B Model Beats Llama-65B NEW BEST LLM!!!
76. How To Create Perfect Prompts for ChatGPT & Midjourney
77. Automate Dataset Creation for Llama-2 with GPT-4!
78. CODE LLAMA - THE BEST CODING MODEL IS HERE!
79. CODE-LLAMA: Is it Actually Good?
80. NEW Friendly Samantha that can Code
81. NEW WizardCoder-34B - THE BEST CODING LLM
82. SmartGPT: Make ChatGPT Smarter
83. Talk to Your Code | Github Repo | Learn How GitHub Co-Pilot & Others Transform Coding 🧠
84. 🚀 MetaGPT Setup: Launch a Startup with One ✍️ Prompt!
85. CODE-LLAMA For Talking to Code Base and Documentation
86. LocalGPT Updates - Tips & Tricks
87. How to use Google PaLM API for Free
88. Mistral 7B -The Most Powerful 7B Model Yet 🚀 🚀
89. Samantha Mistral-7B: Does Fine-tuning Impact the Performance
90. LLaVA - This Open Source Model Can SEE Just like GPT-4-V
91. EASIET Way to Install LLaVA - Free and Open-Source Alternative to GPT-4 Vision
92. Zephyr - 7B Beating Llama-2 70B Model
93. MemGPT: AI Agent 🤖 with Unlimited Memory 🧠 | Store and Load Converstations
94. LM Studio: The Easiest and Best Way to Run Local LLMs
95. NEW "Orca-2" 🐳 Official Release - 13B Better than 70B Models
96. Yi-34B - 200K - The BEST & NEW CONTEXT WINDOW KING 🚀 🚀
97. Neural-Chat 7B: New Best 7B LLM from Intel
98. Your Data, your Model: Fine-Tune Mistral 7B on Custom Data
99. GEMINI 1.0 Beats GPT-4 | The NEW MultiModal Model From GOOGLE
100. Apple Join the AI Race with MLX
101. Mistral - MoE | The Most Unusual Release & How to Run
102. Mistral: Easiest Way to Fine-Tune on Custom Data
103. Mixtral is Now 100% Uncensored 😈 | Introducing Dolphin 2.5- Mixtral 🐬
104. Mixtral MoE on Apple Silicon is Here, thanks to MLX
105. Fine-tune Mixtral 8x7B (MoE) on Custom Data - Step by Step Guide
106. Mistral MoE - Better than ChatGPT?
107. SOLAR-10.7B: Merging Models is The Next Big Thing | Beats Mixtral MoE
108. The Real Progress of Local LLMs
109. Run Mixtral 8x7B MoE in Google Colab
110. TinyLlama: The Era of Small Language Models is Here
111. CrewAI - Your Own Team of Autonomous Agents
112. Custom GPTs are Vulnerable to Prompt Injection 💀💀
113. LocalGPT: Convert Your Chats with Docs to Fine-tuning Datasets
114. OpenAI: New Embedding Models, Price cuts for GPT-3.5, Moderation API and More!!!
115. 🔥 New Gemini Pro Better than GP-4? Huge Performance Boost on ⚔️ Chatbot Arena ⚔️
116. First local LLM to Beat GPT-4 on Coding | Codellama-70B
117. Better RAG: Hybrid Search in Chat with Documents | BM25 and Ensemble
118. World's First Language Processing Unit 🚀 🚀 🚀
119. The Mysterious New LLM from MISTRAL-AI
120. Google Gemma Released | First look at the Technical Report
121. How Bad is Gemma Compared to Mistral?
122. Getting Started with Groq API | Making Near Real Time Chatting with LLMs Possible
123. Chat with Documents is Now Crazy Fast thanks to Groq API and Streamlit
124. Claude 3 Release and The Problem with Benchmarks
125. Ultra Fast LocalGPT inference with Groq API
126. How to Set the Chunk Size in Document Splitter | RAG | LangChain
127. Gemini 1.5 Pro - Coding Assistant with 1M tokens
128. Grok-1 is Open Source | All you need to know!!!
129. What AI Engineering Really Is? Chat with Staff Engineer at CHAI
130. Supercharge Your RAG with Contextualized Late Interactions
131. Voice Cloning with AI
132. Cohere's Command-R+ Specialized Model for RAG and Tools
133. Claude 3 Introduces Function Calling and Tool Usage
134. Taking Function Calling to the NEXT Level with Groq API 🚀 🚀 🚀
135. Mixtral 8x22B MoE - The New Best Open LLM? Fully-Tested
136. Grok Vision - First Multimodal Model from XAi
137. WizardLM 2 - First Open Model Outperforming GPT-4
138. LLAMA 3 Released - All You Need to Know
139. LLAMA-3 🦙: EASIET WAY To FINE-TUNE ON YOUR DATA 🙌
140. Insanely Fast LLAMA-3 on Groq Playground and API for FREE
141. MIXTRAL 8x22B: The BEST MoE Just got Better | RAG and Function Calling
142. Llama-3 Is Not Really THAT Censored
143. Does Size Matter? Phi-3-Mini Punching Above its Size on "BENCHMARKS"
144. How Good is Phi-3-Mini for RAG, Routing, Agents
145. How Good is LLAMA-3 for RAG, Routing, and Function Calling
146. Get your own custom Phi-3-mini for your use cases
147. Extending Llama-3 to 1M+ Tokens - Does it Impact the Performance?
148. Llama-3 🦙 with LocalGPT: Chat with YOUR Documents in Private
149. Free Copilot to Take Your Coding to the NEXT LEVEL
150. Free LOCAL Copilot to Take Your Coding to the NEXT LEVEL
151. ChatRTX: Chat with Documents, Image Search and Voice Input on Windows
152. NVIDIA ChatRTX: Private Chatbot for Your Files, Image Search via Voice | How to get started
153. Yi-1.5: True Apache 2.0 Competitor to LLAMA-3
154. GPT-4o: OpenAI's NEW OMNI-MODEL Can DO it ALL
155. Creating JARVIS - Your Voice Assistant with Memory
156. NEW MISTRAL: Uncensored and Powerful with Function Calling
157. ChatGPT Desktop App: First Impressions and What's Missing!!!
158. Advanced Function Calling with Mistral-7B - Multi function and Nested Tool Usage
159. Master Fine-Tuning Mistral AI Models with Official Mistral-FineTune Package
160. Deploy AI Models to Production with NVIDIA NIM
161. Gemini Flash is SURPRISINGLY Good for Agents and Function Calling
162. Deploy Open LLMs with LLAMA-CPP Server
163. Qwen-Agent: Build Autonomous Agents with The Best Open Weight Model
164. RAG from Scratch in 10 lines Python without Frameworks (LangChain, LlamaIndex, Chroma etc.)
165. RAG from Scratch without any Frameworks
166. Claude Artifacts: What it can do and limitations
167. Self-Host and Deploy Local LLMs with NIMs
168. Google Gemma-2: Technical Report Deep Dive
169. Introducing Gemini API Code Interpreter (Execution)
170. Self-Host and Deploy Local LLAMA-3 with NIMs
171. Making Long Context LLMs Usable with Context Caching
172. Graph RAG: Improving RAG with Knowledge Graphs
173. MOSHI: This is What GPT-4o was Supposed to BE!
174. Graph RAG with Ollama - Save $$$ with Local LLMs
175. Multi-modal RAG: Chat with Docs containing Images
176. Multi-Modal RAG: Chat with Text and Images in Documents
177. ColPali: Vision Language Models for Efficient Document Retrieval
178. GPT-4o mini - Can it be used for Agentic RAG?
179. Private video
180. LLAMA-3.1 405B: Open Source AI Is the Path Forward
181. Just Large Enough - Mistral released a BEAST
182. Create Anything with LLAMA 3.1 Agents - Powered by Groq API
183. LLAMA-3.1 🦙: EASIET WAY To FINE-TUNE ON YOUR DATA 🙌
184. Gemma 2 2B: A Small Model Punching Above its Weight
185. Gemini 1.5 Pro Experimental - New Features with Major Upgrade
186. Custom Chatbots for your Business Needs - No Code Platform
187. Gemini Agents are Surprisingly Good
188. Agents, Agents and more Agents 🤖🤖🤖
189. Will the New GEMINI PDF Feature Replace RAG?
190. Is This the End of RAG? Anthropic's NEW Prompt Caching
191. Creating Low Latency Voice Agents - Open Source 🗣️🗣️🗣️
192. The Hidden Cost of Embeddings in RAG and how to Fix it
193. Try this Before RAG. This New Approach Could Save You Thousands!
194. Not Just Talk: A Voice Assistant That can take Actions
195. Anthropic’s Claude System Prompt Revealed: Key Takeaways for Developers!
196. Is Groq's Reign Over? Cerebras Sets a New Speed Record!
197. Run Uncensored LLAMA on Cloud GPU for Blazing Fast Inference ⚡️⚡️⚡️
198. I Tested the AI Code Editor Everyone’s Talking About—Here’s What Happened!
199. ColPali: Vision-Based RAG System For Complex Documents
200. The Reflection 70B Drama and How Good it is?
201. OpenAI O1 Can Reason—But How Good Is It?
202. O1’s Chain of Thought: I Built a System to Mimic It—Here’s How It Went!
203. Can VISION Language Models Solve RAG? Introducing localGPT-Vision
204. The Best RAG Technique Yet? Anthropic’s Contextual Retrieval Explained!
205. EASIEST Way to Fine-Tune LLAMA-3.2 and Run it in Ollama
206. Contextual Retrieval with Any LLM: A Step-by-Step Guide
207. OpenAI DevDay 2024 - What No One is Talking About!
208. OpenAI Canvas First Impressions: Will It Replace Your Coding Assistant?
209. Goodbye Text-Based RAG, Hello Vision AI: Introducing LocalGPT Vision!
210. Stop Losing Context! How Late Chunking Can Enhance Your Retrieval Systems
211. How OpenAI’s SWARM Simplifies Multi-Agent Systems
212. LightRAG: A More Efficient Solution than GraphRAG for RAG Systems?
213. NotebookLM: Its More than AI Podcasts- Your Personalized AI Research Assistant
214. Meta New Models - SAM 2.1, Spirit LM, MEXMA and More
215. Local LightRAG: A GraphRAG Alternative but Fully Local with Ollama
216. Claude 3.5 Sonnet Upgrade + New API to Control Your Computer – First Look
217. Ollama with Vision - Enabling Multimodal RAG
218. Qwen 2.5 Coder 32B: Is This Best Open Weight Model Better than GPT-4o?
219. OpenAI O1 Tested: Smarter, But Is It Truly Reliable?
220. The New Gemini Experimental: Can it Pass the Reasoning Tests?
221. DeepSeek v3: The First Open Model to Rival OpenAI and Anthropic!
222. Meet KAG: Supercharging RAG Systems with Advanced Reasoning
223. Anthropic’s Blueprint for Building Lean, Powerful AI Agents
224. SmolAgents: A Smol Library to Build Agents
225. Build Multi-Agent Systems with SmolAgents
226. Falcon 3: New Multimodal AI Model for Text, Image, and Video Understanding
227. Google's Blueprint to Building Powerful Agents
228. Easiest Way to run Private RAG on Windows
229. DeepSeek-R1 is here! First Open O1 level Model
230. Deepseek R1 [Tested]: Is it Actually Worth the HYPE?
231. DeepSeek vs. Gemini Flash vs. GPT-4: AI Search Showdown
232. DeepSeek - Goes Mainstream, Everybody In Panic
233. The Real Reason NVIDIA Stock Crashed—And It’s NOT What you Think!
234. The Real Reason NVIDIA Stock Crashed—And It’s NOT What you Think!
235. Llama 4, DeepSeek & the AI Copyright Wars—Dario Weighs In
236. O3 Mini, Mistral, Gemini Flash and DeepSeek—The AI Race Is Heating Up!
237. OpenAI O3 Mini: Faster, Smarter, But Is It Better?
238. O3 Mini - Hands On: The New AI Search & Coding King?
239. OpenAI’s O3 Mini vs. DeepSeek R1: Which One Wins?
240. Gemini 2.0 Pro
241. Gemini 2.0 Flash vs. Flash-Lite: Which One Should You Use?
242. Supercharge Your RAG with DeepSeek's Reasoning Model
243. Did xAI Cheat? The Truth About Grok-3’s Benchmarks!
244. Diffusion LLMs Are Here! Is This the End of Transformers?
245. GPT-4.5: OpenAI’s Most Interesting Model Yet?
246. DeepSeek’s 500% Profit Margin—How Are They Doing It?
247. Supercharge Your RAG with DeepSeek's Reasoning Model
248. Reward Hacking in LLMs Explained
249. Google’s Gemma 3: The Best Open-Weight Model Yet?
250. OpenAI’s Responses API: The Easiest Way to Build a RAG System?
251. Mistral Small but Mighty - Apache 2.0, Multimodal & Fast
252. DeepSeek Just Updated—The Best Coding Model Yet?
253. GPT-4o’s Upgrade is Kinda Wild (Coding, Images, Unhinged Mode?)
254. Q Developer - AI Coder Built for Scale - Code, Review, Ship
255. Model Context Protocol (MCP) Explained: The New Standard for AI Tools?
256. Forget Next-Word Prediction—LLMs Are Doing This Instead ...
257. MCP Security is Still Broken
258. Quasar Alpha: This Mystery Coding Model is So Cracked 🔥
259. Same LLaMA 4 Models, 5 Providers—Very Different Results!
260. GPT-4.1: Everything You Need to Know (+ What OpenAI Didn’t Say)
261. 🚀 GPT-4.1 Is Great at Coding, But I Won’t Use It. Here’s Why!
262. Google’s AI Studio in 22 Minutes
263. OpenAI O3 & O4 Mini: The First True Reasoning Agents?
264. OpenAI O3: A Breakthrough in Agentic Coding?
265. Gemini 2.5 Flash - Hybrid Reasoning on Demand
266. Gemini 2.5 Flash - Hybrid Reasoning on Demand
267. Building AI Agents That Work - My Talk at Google NEXT
268. Qwen-3 Is Here — The Llama-4 We’ve Been Waiting For!
269. GPT‑4o’s “Yes‑Man” Personality Issue—Here’s How OpenAI Fixed It
270. Gemini 2.5 Pro's: The Best Coding Model Just got Better
271. Is Deep Agent the Manus/Genspark Killer?
272. New Anthropic Study: AIs Hide Plans, Cheat Quietly
273. No Chunks, No Embeddings: OpenAI’s Index‑Free Long RAG
274. Google’s New Stack: Gemini On-Prem, ADK, Open Models -- Interview
275. OpenAI Codex Agent – Is This the End of Programmers?
276. Google's VEO: The Cheapest Way to Use the Best AI Video
277. Jules: Google’s Codex Killer?
278. From Models to Agentic Applications with Sam Witteveen
279. Gemini Diffusion Is CRAZY Fast—But Not What You Think
280. Context Engineering for Building Better Agents
281. LocalGPT 2.0: Turbo-Charging Private RAG
282. Warp: The CLI Agent That Could Replace Claude Code
283. The Only Embedding Model You Need for RAG
284. Context Engineering — The Hottest Skill in AI Right Now
285. Secret Context Engineering Trick For RAG
286. Grok 4—Possibly the Most Powerful Model in the World?
287. Kimi K2 - The DeepSeek Moment for Agentic Coding?
288. Kimi K2 — The Deep Researcher Agent
289. NEW Qwen 3 Coder: Did the Benchmark Lie?
290. GPT-5 - A Good Coding Model?
291. Gemini Deep Think: Built for the Hardest Problems
292. LangExtract: Turn Messy Text into Graph-RAG Insights
293. GPT-5 Coding Agent vs. Real App: What It Actually Built in Cursor
294. GPT-5: The Most Polarizing Model
295. LangExtract + RAG: Smarter Retrieval with Metadata Filtering
296. GPT-OSS: Same Model, Different Results?!
297. GPT-OSS Jailbreak: No Fine-Tuning, No Hacks—One Simple Trick
298. Finally! A Standard for AI Coding Agents (Agents.md Explained)
299. DeepSeek V3.1: Bigger Than You Think!
300. Nano Banana is the NEW Gemini 2.5 Flash Image
301. The EASIEST Way to Scrape Any Website
302. Solving Context Loss Due to Chunking with Contextualized Embeddings
303. Claude for Chrome: Agentic Browsing is Here
304. Embedding Gemma: On-Device RAG Made Easy
Is Vicuna the ChatGPT Killer?
GD
General Discussion
Chapter doubts and student replies
?
Be the first to ask a doubt in this chapter.
0/1000
In this video, I will show you how to use Vicuna-13B, an open-source chatbot that claims to achieve 90% * quality of ChatGPT and Google Bard. I will also test its performance on various questions and compare it with other models. Vicuna-13B is trained on user-shared conversations from ShareGPT and fine-tuned on LLaMA. It is backed by an enhanced dataset and an easy-to-use, scalable infrastructure. Watch this video to learn more about this chatbot and see how it performs. The results are impressive and are comparable to the responses of the ChatGPT. Vicuna 13B is an impressive model and could be a potential competitor to other Open-sourced models. Preliminary evaluation using GPT-4 as a judge shows Vicuna-13B achieves more than 90%* quality of OpenAI ChatGPT and Google Bard while outperforming other models like LLaMA and Stanford Alpaca in more than 90%* of cases. ☕ Buy me a Coffee: https://ko-fi.com/promptengineering Vicuna Blogpost: https://vicuna.lmsys.org/ Vincua Demo: https://chat.lmsys.org/ GPT-4 Assessment website: https://vicuna.lmsys.org/eval/ FastChat Github: https://github.com/lm-sys/FastChat ShareGPT: https://sharegpt.com/ Keywords: Vicuna-13B, open-source chatbot, ChatGPT, Bard, LLaMA, ShareGPT
Frequently Asked Questions
Yes, TutoHub provides this course and all its materials completely free of charge. You can learn at your own pace without any subscriptions.
No, your progress and notes are automatically saved in your browser's local storage. However, creating an account helps you sync progress across devices.
Prerequisites depend on the course topic, but most of our content is designed to be beginner-friendly. Check the "About" section for specific requirements.
Study Notes
College Project Help?
Need a minor/major project? Or stuck in coding? Get expert help and book a free weekend class.
Get Help Now