![Ai Flux](/img/default-banner.jpg)
- 980
- 27 882 995
Ai Flux
United States
Приєднався 28 вер 2022
Keep up with the latest in advancements in Generative AI, LLM's and more!
All content is created by Noah, an established professional Machine Learning engineer.
Send us a DM on twitter or email aifluxcollaboration@mailfence.com if you'd like us to cover something specific or would like to collaborate with our channel!
All content is created by Noah, an established professional Machine Learning engineer.
Send us a DM on twitter or email aifluxcollaboration@mailfence.com if you'd like us to cover something specific or would like to collaborate with our channel!
AiDer v0.50 : INFINITE output for DeepSeek Coder, Mistral Coding LLMs
Introducing AIder v0.50, the game-changer for coders! Unlocking limitless potential, AIder generates endless code solutions for DeepSeek Coder and Mistral Coding LLMs. Say goodbye to coding blocks and hello to innovation. Watch as AIder becomes your ultimate coding companion, boosting productivity and creativity.
Let us know what you think in the comments below!
Link to X post: x.com/paulgauthier/status/1823447077286010974
Aider Website: aider.chat/docs/llms.html
Aider Github: github.com/paul-gauthier/aider
Let us know what you think in the comments below!
Link to X post: x.com/paulgauthier/status/1823447077286010974
Aider Website: aider.chat/docs/llms.html
Aider Github: github.com/paul-gauthier/aider
Переглядів: 8 695
Відео
🦙✨ BigLlama-3.1-1T-Instruct: 1 TRILLION Parameter Llama Merge (Melts GPUs)
Переглядів 3,6 тис.14 днів тому
🦙✨ BigLlama-3.1-1T-Instruct: 1 TRILLION Parameter Llama Merge (Melts GPUs)
BRX 🧱 20B: San Francisco AI Devs Create a NEW LLM Language
Переглядів 3 тис.14 днів тому
BRX 🧱 20B: San Francisco AI Devs Create a NEW LLM Language
Flux.1 16B: New SOTA Text 2 Video Model by Black Forest Labs (Ex-Stability AI)
Переглядів 11 тис.14 днів тому
Flux.1 16B: New SOTA Text 2 Video Model by Black Forest Labs (Ex-Stability AI)
Mistral Large 2 123B: DEFEATS Llama 405B with Coding & AI Agents!
Переглядів 15 тис.Місяць тому
Mistral Large 2 123B: DEFEATS Llama 405B with Coding & AI Agents!
Meta Llama 3.1-405B Explained: The FUTURE of AI is OPEN-SOURCE!
Переглядів 4,4 тис.Місяць тому
Meta Llama 3.1-405B Explained: The FUTURE of AI is OPEN-SOURCE!
Llama 3.1-405B Model LEAKED! New Benchmarks Hint at GPT-4o Takedown?
Переглядів 3,5 тис.Місяць тому
Llama 3.1-405B Model LEAKED! New Benchmarks Hint at GPT-4o Takedown?
Deepseek Coder v2 just one-shot fixed the CrowdStrike Cyber Incident?
Переглядів 2,1 тис.Місяць тому
Deepseek Coder v2 just one-shot fixed the CrowdStrike Cyber Incident?
Mistral NeMo 12B: The Instruct Model for Coders & AI Agents - Supercharge Your Workflow
Переглядів 6 тис.Місяць тому
Mistral NeMo 12B: The Instruct Model for Coders & AI Agents - Supercharge Your Workflow
Llama 3-405B is Coming! 🚀 (on WhatsApp?)
Переглядів 2,9 тис.Місяць тому
Llama 3-405B is Coming! 🚀 (on WhatsApp?)
💊 MentatBot 🤖 : NEW Advanced AI Coding Agent that BEATS Devin and Codestral!
Переглядів 3 тис.Місяць тому
💊 MentatBot : NEW Advanced AI Coding Agent that BEATS Devin and Codestral!
Chinese AI models storm Hugging Face's Open LLM Leaderboard!
Переглядів 3 тис.Місяць тому
Chinese AI models storm Hugging Face's Open LLM Leaderboard!
Meet Sohu, the fastest AI chip of all time.
Переглядів 21 тис.2 місяці тому
Meet Sohu, the fastest AI chip of all time.
Claude 3.5 INSANE Coding Ability & beats GPT-4o AND Llama3-400B
Переглядів 6 тис.2 місяці тому
Claude 3.5 INSANE Coding Ability & beats GPT-4o AND Llama3-400B
DeepSeek-Coder-V2: First Open Source Coding Model Beats GPT4-Turbo
Переглядів 21 тис.2 місяці тому
DeepSeek-Coder-V2: First Open Source Coding Model Beats GPT4-Turbo
🐍 Mamba2 8B Hybrid 🚀: NVIDIA Stealth drops their latest Mamba2 Model!
Переглядів 4,1 тис.2 місяці тому
🐍 Mamba2 8B Hybrid 🚀: NVIDIA Stealth drops their latest Mamba2 Model!
NVIDIA Nemotron 4 340B: Using LLMs to Create Models that OUTPERFORM GPT-4o
Переглядів 6 тис.2 місяці тому
NVIDIA Nemotron 4 340B: Using LLMs to Create Models that OUTPERFORM GPT-4o
New nVidia 5090 Leaks! GB202 is MASSIVE Leap for Local AI!
Переглядів 2,3 тис.2 місяці тому
New nVidia 5090 Leaks! GB202 is MASSIVE Leap for Local AI!
Stable Diffusion 3: Model Weights Released! The Future of AI Art is Open!
Переглядів 6 тис.2 місяці тому
Stable Diffusion 3: Model Weights Released! The Future of AI Art is Open!
Qwen 2 LLM Unleashed: The SMALLEST Model That Can Outcode Llama 3?
Переглядів 4,4 тис.2 місяці тому
Qwen 2 LLM Unleashed: The SMALLEST Model That Can Outcode Llama 3?
ChatGPT is down, now what? Cyberattack?
Переглядів 3,2 тис.2 місяці тому
ChatGPT is down, now what? Cyberattack?
Stable Diffusion 3 Open Release Date Announced! AMD Acquisition?
Переглядів 4,5 тис.2 місяці тому
Stable Diffusion 3 Open Release Date Announced! AMD Acquisition?
NVIDIA CEO Jensen Huang Reveals AI Future: "NIMS" Digital Humans, AI Factories and Digital Earth!
Переглядів 4,3 тис.2 місяці тому
NVIDIA CEO Jensen Huang Reveals AI Future: "NIMS" Digital Humans, AI Factories and Digital Earth!
Hugging Face just got H*CKED?! Are your GPUs safe?
Переглядів 4,3 тис.2 місяці тому
Hugging Face just got H*CKED?! Are your GPUs safe?
Neural DareDevil-8B 😈: The fastest LLama3 8B Finetune + Merge on earth!
Переглядів 3,4 тис.2 місяці тому
Neural DareDevil-8B 😈: The fastest LLama3 8B Finetune Merge on earth!
🇫🇷 Mistral AI's NEW 22B Coding Model with Code Inpainting 🎨 Beats DeepSeekCoder 33B!
Переглядів 12 тис.2 місяці тому
🇫🇷 Mistral AI's NEW 22B Coding Model with Code Inpainting 🎨 Beats DeepSeekCoder 33B!
AI Experts MERGED! 🐬 Mistral-1x-22b is BENDING THE RULES (SLERP Explained)
Переглядів 4,8 тис.2 місяці тому
AI Experts MERGED! 🐬 Mistral-1x-22b is BENDING THE RULES (SLERP Explained)
MASSIVE Leap for LLama3! OpenChat's 3.6 8B Model Obliterates LLama3 8B!
Переглядів 6 тис.2 місяці тому
MASSIVE Leap for LLama3! OpenChat's 3.6 8B Model Obliterates LLama3 8B!
NVIDIA just made Local AI 3X Faster on Windows??
Переглядів 7 тис.3 місяці тому
NVIDIA just made Local AI 3X Faster on Windows??
NEW Mistral-7B v0.3 🇫🇷 TESTED: Uncensored, Function Calling, faster than llama3 8b?!
Переглядів 4,7 тис.3 місяці тому
NEW Mistral-7B v0.3 🇫🇷 TESTED: Uncensored, Function Calling, faster than llama3 8b?!
🗣 luisa mel
Se parece a mi en el caminar😂
When they start eating u, u won't laugh 😒
Marche pareille comme beden 😮
They must have programmed it to do Biden's walk
I have already tested a few models myself and am really impressed by some of them. However, they all reach their limits. But there is something else that is currently bothering me. I don't really want to have to explain to the coding assistant the context in which the whole thing is happening. I actually want to give it my entire project and work in a larger context. e.g. a Python programme with 10 files, then it should know all 10 files. Let's say it's a programme that somehow stores people in a database and displays them as a webpage. If I then say that I want to save the date of birth for each person, then it should suggest how the database should be adapted, how the dataclass files should be changed, how the input should be validated and how the UI should be adapted.... This task is actually not that difficult, but requires a much larger context. All models don't have that and I really miss something like that. I currently use the CodeGPT plugin for JetBeans IDEs. Does anyone have a good idea how I can better realise my wish?
I need a 🤖 robot to clean my house😂 Your price will be mine 😊.
Why is the “encoded” prompt in the example longer than the original English prompt? What’s the benefit?
Good
I'm counting 52 points of articulation assuming 2 per finger
That must be the hands free version
Sera que esse.pessoal querem um voluntario pra adapitar uma perna bionica dessa sou amputado
Sembra Steven quello del film" otto sotto un tetto"😂😂😂🤭
Ha Alzheimer?
Программа была в оперативной памяти. А запущенная пргграмма очень слпто нагркжает устройство .
UBI 2027
Universal Basic Income
qwen0.5b require not much ram, but how it generate so fast?
Εντάξει το καταλαβαίνει τι θέλετε να μας κάνετε για φαντάσου να γυρίσει η βίδα τους ανάποδα προς εσας όπως αρχίζει να γυρνάει η δική μας
Will this work on 3090? and 4090 P2P? I have 2 of each... Thanks!
Sso you just read documentation bravo!🎉
In the future, robots will remember what this guy did and will hunt him down.
aider is by far the most useful AI tool that I use
What kind of coding do you generally use it for?
Should have wider feet for stability.
These things are useless....we will never design an AI as good as the human brain
Stop Al 😮
😂 sorria agora, no futuro vcs choran 😢😢😢
What device is it?
e-reader
Can it wash dishes, vacuum, and clean the bathroom?
The 4070 and 4070 Super don't have 16GB vram they have 12...... (10:00 mark)
🙂👍👍👍👍...
Ini menandakan bahwa ciptaan Allah lebih sempurna dari ciptaan yang diciptakannya.
More live coding to learn your process
Been using aider for a couple months now, daily. Deepseek is definitely not on par with sonnet 3.5 in regards to quality, speed. Sonnet gets it right forst time 80% of the time whereas deepseek makes errors or gets it right about 50% of the time. Big difference
😮😮
로봇은 이 일을 기억할 것이다
I like aider browser, but am i mistaken or when using it you can't use many of the useful commands like /ask or /help because those are aider terminal commands?
these progress in coding ai makes me want to learn to code, I feel like the creation potential is expanding exponentially
Ugly robot 😂😂😂
Friend im trying my best but your videos are so rambley, I still dont fully understand what this video is about.
use Perplexity, paste the video url in it and ask whatever you want
Aider soort pair programming with an ai tool he just goes over the feature set
Это очень страшно.
Bestagem
I also use LLMs a lot for building dictionaries or formating stuff the way in need it in my code!
A single H100 cannot fit this model at full precision as it is 256GB in size. It must use multiple H100s or be quantized to 4bit
Gemini is also a very good coding model but Gemini shines in chemistry! It's unbelievable when using it for chemical stuff.
What kind of chem / computational chem have you used it for?? I actually considered doing a PhD in comp chem :)
I tried to use this with deepseek-coder-v2 lite, the 16B, but it's too weak to do anything right past the first prompt. I kinda wish there was a 70B version on ollama. Should i try with another like llama 3.1 70B? Would it work much better than deepseek lite?
no, you should use deepseek v2 through the api, it's a 236B model. LLama 3.1 can't even follow aider's format and needs to be reprompted multiple times, not to mention that it is quite weak at coding.
@@sorenkirksdjfk7310 i was looking for something to experiment on without using money
I do agree the 16B model is basically only useful for things like basic javascript and beginner bash scripting. API's are really cheap though if you don't want to run something locally.
If you want the best results possible then use Claude 3.5 Sonnet, followed by GPT 4-o and DeepSeek Coder V2. Different LLMs are built for different use cases and you're wasting your time trying to code with these locally hosted small LLMs. The technology just isn't there yet, so APIs are your best bet as of now.
To infinity and beyond ! 👋👍
Thanks!
Boston Dynamics is killin' the game right now
I am still putting print statements in my code to debug it sorry not jumping this band wagon until I am pulled on kicking and screaming.
Well people said the same thing when electricity and the telephone first came out😂
I have heard about this. Let's see it in use.
Going to do this in the livestream next week ;)