Hugging Face – Posts

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

All HF Hub posts

Join Posts waitlist

singhsidhukuldeep

posted an update about 2 hours ago

Post

149

Is GPT-4o everything you expected? 🤔

@OpenAI has gone omni (GPT-4"o" 🌐), a multimodal LLM, it accepts as input any combination of text, audio, and image and generates any combination of text, audio, and image outputs. 🎤📸✏️

1️⃣ Based on the examples seen:
Inputs possible are Text ✏️, Text + Image 📝🖼️, Text + Audio 📝🎧, Text + Video 📝🎥, Audio 🎧
and outputs possible are Image 🖼️, Image + Text 🖼️📝, Text 📝, Audio 🎧

2️⃣ 88.7% on MMLU 🏆; 90.2% on HumanEval (best in class) 🥇

3️⃣ Up to 50% cheaper 💸 and 2x faster ⚡ than GPT-4 Turbo

4️⃣ GPT-4o will be available in the free tier of ChatGPT 🎉

5️⃣ Near real-time audio with 320ms on average, similar to human conversation 🗣️**

6️⃣ New tokenizer with a 200k token vocabulary 📚 (previously 100k vocabulary) leading to 1.1x - 4.4x fewer tokens needed across 20 languages 🌍

7️⃣ Tokenizer compression and more efficient across non-English languages (3-5 times fewer tokens for major Indian languages 🇮🇳)

👐Open questions:
- What is the context length? ❓
- Why does GPT-4 still exist, if GPT-4o is better, faster, and cheaper? 🤨

Blog: https://openai.com/index/hello-gpt-4o/🌐
Available today:https://chatgpt.com/ 🚀

I just wanted it to be cheaper, and more accessible! 🙌

Still not open source, but a price reduction is welcome! 💰

Also, something fun happened, for the first 10-15 mins all search engines were correcting GPT-4o to GPT-4 😂

Also, also, GPT-4o is the model which was powering the GPT2 chatbot in the LMsys arena (ELO 1310 vs. 1253 for GPT-4 Turbo) 🏅

tomaarsen

posted an update about 3 hours ago

Post

225

NuMind has just released 3 new state-of-the-art GLiNER models for Named Entity Recognition/Information Extraction. These GLiNER models allow you to specify any label that you want, and it'll find spans in the text corresponding to your label. It's been shown to work quite well on unusual domains, e.g. celestial entities in my picture.

There are 3 models released:
- numind/NuNER_Zero:
The primary model, SOTA & can detect really long entities.
- numind/NuNER_Zero-span:
Slightly better performance than NuNER Zero, but can't detect entities longer than 12 tokens.
- numind/NuNER_Zero-4k:
Slightly worse than NuNER Zero, but has a context length of 4k tokens.

Some more details about these models in general:
- They are *really* small, orders of magnitude smaller than LLMs, which don't reach this level of performance.
- Because they're small - they're fast: <1s per sentence on free GPUs.
- They have an MIT license: free commercial usage.

Try out the demo here: numind/NuZero
Or check out all of the models here: numind/nunerzero-zero-shot-ner-662b59803b9b438ff56e49e2

If there's ever a need for me to extract some information from any text: I'll be using these. Great work @Serega6678 !

2 replies

Kvikontent

posted an update about 5 hours ago

Post

294

I just created a simple LoRA model which is trained just on 106 images and got super model, which became a little bit popular, 6k downloads at total, which is a lot for me, just small programmer, with low laptop!
Kvikontent/midjourney-v6

Jaward

posted an update about 6 hours ago

Post

401

Build your own GPT-4 Tokenizer! - @karpathy 's minbpe exercise.
Step 1: BasicTokenizer
Got "close" to beating minbpe's train speed :(
step 2 RegexTokenizer coming soon.

Notes on lessons learned:
- tokenization is the assembly language of LLMs:)
It's not a healthy choice to code it lol.
- encoding can literally drive you mad.
- merging is where sh*t gets real - moment of truth:)
- training requires precision.
- decoding is trivial.

ajithprabhakar

posted an update about 7 hours ago

Post

434

Can AI cheat or lie?

In this blog, we will explore the research conducted by experts from MIT, Australian Catholic University, and the Center for AI Safety to better understand the nature of AI deception, its various forms, and the potential risks it poses. We will examine real-world examples and the underlying mechanisms that enable AI systems to deceive.

Learn more at: https://ajithp.com/2024/05/12/ai-deception-risks-real-world-examples-and-proactive-solutions/

jbilcke-hf

posted an update about 9 hours ago

Post

738

Added a new button to the AI Stories Factory for more fun!

jbilcke-hf/ai-stories-factory

1 reply

HeshamHaroon

posted an update about 10 hours ago

Post

613

Hey everyone! Just wanted to share this awesome dataset that features over 1 million tokens specifically for the Egyptian dialect. Check it
HeshamHaroon/1milion_token_EGY_songs

Yoben

posted an update about 10 hours ago

Post

442

IBM has launched its latest #Granite code models.
𝗚𝗿𝗮𝗻𝗶𝘁𝗲 𝗼𝗻 𝗛𝘂𝗴𝗴𝗶𝗻𝗴 𝗙𝗮𝗰𝗲 - https://lnkd.in/g2KaHWxC
The figure illustrates how#Granite-8B-Code-Base outperforms #Mistral-7B, #LLama-3-8B, and other open-source models in coding tasks.

Models available:
- ibm-granite/granite-3b-code-base
- ibm-granite/granite-3b-code-instruct
- ibm-granite/granite-8b-code-base
- ibm-granite/granite-8b-code-instruct
- ibm-granite/granite-20b-code-base
- ibm-granite/granite-20b-code-instruct
- ibm-granite/granite-34b-code-base
- ibm-granite/granite-34b-code-instruct

standardAI

posted an update about 10 hours ago

Post

351

Hi @TimothyAlexisVass , thanks for [this great blog post](https://huggingface.co/blog/TimothyAlexisVass/explaining-the-sdxl-latent-space#the-4-channels-of-the-sdxl-latents)! Shouldn't this be like that?
https://github.com/TimothyAlexisVass/hf-colorspace-blogpost/pull/1

QagentS

posted an update about 10 hours ago

Post

387

Hi folks ,

colab[https://colab.research.google.com/drive/10av3SxFf0Psx_IkmZbcUhiVznStV5pVS?usp=sharing]

#OpenSourcing
pip-code-bandit
-- a model to act as intelligence unit in agentic workflows.

pipflow
-- a library to manage and run goal oriented agentic system.

pip-code-bandit attributes-
-- number of params ~ 1.3b [2.9 Gb GPU memory footprint]
-- sequence length ~ 16.3k [Can go higher but will show performance degradation]
-- license - apache 2.0
-- instruction following , RL tuned.
-- tasks:
complex planning(plan) of sequential function calls | a list of callables and goal
corrected plan | feedback instructions with error
function calling | doc or code and goal
code generation | plan and goal
code generation | goal
doc generation | code
code generation | doc
file parsed to json | any raw data
sql generation | schema, question, instructions and examples

#Strategy

We used a simulator to simulate environments where the model could play games to achieve goals, given a set of actions available to it. All the model could do was find the right action and config to incur a positive reward. The reward policy is around the concept of a model going to a stable state of zero net sum reward for both good and bad behaviour. In this setup, the model, which was pre-trained on code, function documentation, and similar OS datasets, was RL-tuned for reliability and instruction-following.

Do try it out and let me know how its working for you.

Thank you :)

Recently active users