Yi Cui

onekq

AI & ML interests

Benchmark, Code Generation Model

Recent Activity

View all activity

Organizations

MLX Community's profile picture ONEKQ AI's profile picture

onekq's activity

replied to CadenHolman's post 1 day ago
reacted to CadenHolman's post with 👀 1 day ago
view post
Post
1455
We’re excited to launch CodeDebugger.ai, a free, privacy-first tool that helps developers debug code instantly using AI.

What it does:

Paste your code (PHP, JavaScript, HTML, SQL, and more)

Get AI-generated bug reports and improvement suggestions

No sign-up, no tracking — each result link expires in 24 hours

Why we built it: Every developer hits walls. Whether you're stuck on a syntax bug or need another set of eyes, CodeDebugger.ai offers instant feedback powered by OpenAI models — all without compromising your privacy.

Privacy-first by design:

No login required

Code is deleted after 24 hours

No analytics, no tracking, no cookies

Try it now:
https://CodeDebugger.ai
  • 2 replies
·
replied to clem's post 2 days ago
view reply

That's a great start. Also see my post https://huggingface.co/posts/onekq/992154552707771

The point is models are already embedded and inferenced everywhere. If you standardize energy consumption as a inference output field, your impact is multiplied instantly because the groundwork is already there.

In theory, this works for closed-source model too.

posted an update 2 days ago
view post
Post
1799
I've recently attended a panel on AI applications. The panelists are managers/directors of Fortune 500 companies. These people make things happen and own results, so their stories and pain points are fresh.

(1) Models are used EVERYWHERE, customer facing and internal support, etc.
(2) A successful application must improve one of the following: revenue (💵💵), cost (💵💵), CSAT (still 💵💵)
(3) They proactively search on 🤗HF🤗 for models and use them. Open source models (especially small ones) can flexibly fit into their existing workflows/infras, which enable them to deliver, and fast.
(4) The main barrier for adoption is license. A director told me they picked a model and finetuned it, then learned they would have to share enhancements. As a result, they dropped this model and the million dollar impact went to another model.

So to fellow model builders:
(1) celebrate that our work is useful and generate lots of values
(2) make your license permissive if you want maximum impact
  • 1 reply
·
replied to clem's post 3 days ago
view reply

Also would be great to have this in API response, then you have energy-aware leaderboards, workflows, etc.

replied to their post 3 days ago
view reply

Also llama-server ... you don't use Ollama?

reacted to clem's post with 🔥 3 days ago
view post
Post
3713
Energy is a massive constraint for AI but do you even know what energy your chatGPT convos are using?

We're trying to change this by releasing ChatUI-energy, the first interface where you see in real-time what energy your AI conversations consume. Great work from @jdelavande powered by spaces & TGI, available for a dozen of open-source models like Llama, Mistral, Qwen, Gemma and more.

jdelavande/chat-ui-energy

Should all chat interfaces have this? Just like ingredients have to be shown on products you buy, we need more transparency in AI for users!
  • 3 replies
·
replied to their post 3 days ago
view reply

I meant the model adoption. When the bugs are being fixed, the window of opportunity (recent launch) has passed.

replied to their post 4 days ago
posted an update 4 days ago
view post
Post
793
Heard good things about this model and no inference providers support it ...

THUDM/GLM-4-9B-0414
  • 6 replies
·
replied to their post 5 days ago
view reply

This requires philosophical minds. I am quite sure authors themselves as technologists didn't think about these when they wrote it.

posted an update 6 days ago
view post
Post
413
This post discussed the same trend as the Sutton post, but is more concrete and down-to-earth.

https://ysymyth.github.io/The-Second-Half/

Two takeaways for me. (1) deep neural network is the backbone to unify everything. RLHF will stand the test of time because it brings two distinct fields (NLP and RL) onto the same model weights. (2) language model will continue to play a central role in the era of agent. It probably won't be the end game to AGI, but definitely not offramp.
reacted to JLouisBiz's post with 🔥 6 days ago
view post
Post
2067
Back to LLM integration.

ClickDefine.sh -- quickly define or explain anything within your whole desktop environment

You only need to run the model locally, maybe with the **llama.cpp** or **ollama**

- https://github.com/ggml-org/llama.cpp
- https://ollama.com/download

And you get universal explaining tool that works anywhere on your X Org Desktop (on operating systems which are usually Fully Free Software like Debian GNU/Linux)

ClickDefine - Interactive Text Processor Script for Iterative LLM Query Handling:
https://hyperscope.link/9/6/0/9/8/ClickDefine-Interactive-Text-Processor-Script-for-Iterative-LLM-Query-Handling-96098.html

Watch the demonstration here: https://www.youtube.com/watch?v=mQxCYAiReu0&t=2s
posted an update 8 days ago
view post
Post
1515
This is bitter lesson 2.0
https://storage.googleapis.com/deepmind-media/Era-of-Experience%20/The%20Era%20of%20Experience%20Paper.pdf

If this reads too lofty to you, consider some low-hanging fruits. Experiences here are reward signals we send to LLMs, e.g. human score in RLHF, verification in AlphaProof, or test results for code generation.

RFT (reinforced finetuning) will become main stream, and IMO make LLMs behave more like agents.
  • 2 replies
·
replied to their post 8 days ago
posted an update 9 days ago
reacted to JLouisBiz's post with 👀 9 days ago
view post
Post
1386
https://www.youtube.com/watch?v=84iS3atFQdI

**Speech typing in Emacs** by using NVIDIA Canary 1B model in multiple languages

This video showcases a demonstration of speech-to-text capabilities within the popular text editor, Emacs, utilizing the advanced NVIDIA Canary 1 Billion parameter (1B) language model. The presentation highlights how users can effectively type and edit documents across various programming or markup languages using spoken commands.

The demo likely illustrates seamless integration between cutting-edge AI technology from NVIDIA's Canary series—known for its powerful natural language processing capabilities—and Emacs, a highly customizable text editor favored by developers worldwide. By leveraging the 1B model, which is capable of understanding context and nuances in multiple human languages, users can dictate their code or prose directly into Emacs with impressive accuracy.

The video probably covers how this setup supports several different programming languages as well as natural language typing tasks, showcasing its versatility across various domains such as software development and content creation. Additionally, the demonstration may include examples of real-time transcription performance in diverse linguistic contexts to emphasize the model's multilingual proficiency.

Overall, viewers can expect insights into enhancing productivity by integrating AI-driven speech recognition directly within their text editing workflow using Emacs paired with NVIDIA’s advanced language models.
reacted to ZennyKenny's post with 🤗 9 days ago
view post
Post
1415
Submitted my first dataset for the Reasoning Datasets Competition! ZennyKenny/TRON-dataset-v.1.0

This dataset is designed to post-train Metareasoning agents, or those agents whose job it is to quickly (and importantly, cheaply) reason through whether it makes sense to launch a full reasoning job or simply use a simple completions job.

There's still plenty of time to join the competition! https://www.bespokelabs.ai/blog/reasoning-datasets-competition

Generation notebook (linked in dataset) is open source and pretty well generalized if I don't say so myself, so you can use it to make your own Metareasoning datasets.

Shoutout to @onekq for his inspiring comment on this topic.
posted an update 10 days ago
posted an update 11 days ago