text-generation-inference (Text Generation Inference)

clem

posted an update 7 days ago

Post

1522

Coming back to Paris Friday to open our new Hugging Face office!

We're at capacity for the party but add your name in the waiting list as we're trying to privatize the passage du Caire for extra space for robots 🤖🦾🦿

https://t.co/enkFXjWndJ

1 reply

·

Narsil

posted an update 13 days ago

Post

936

Performance leap: TGI v3 is out. Processes 3x more tokens, 13x faster than vLLM on long prompts. Zero config !

3x more tokens.

By reducing our memory footprint, we’re able to ingest many more tokens and more dynamically than before. A single L4 (24GB) can handle 30k tokens on llama 3.1-8B, while vLLM gets barely 10k. A lot of work went into reducing the footprint of the runtime and its effect are best seen on smaller constrained environments.
13x faster

On long prompts (200k+ tokens) conversation replies take 27.5s in vLLM, while it takes only 2s in TGI. How so ? We keep the initial conversation around, so when a new reply comes in, we can answer almost instantly. The overhead of the lookup is ~5us. Thanks @Dani ël de Kok for the beast data structure.
Zero config

That’s it. Remove all the flags your are using and you’re likely to get the best performance. By evaluating the hardware and model, TGI carefully selects automatic values to give best performance. In production, we don’t have any flags anymore in our deployments. We kept all existing flags around, they may come in handy in niche scenarios.

Read more: https://huggingface.co./docs/text-generation-inference/conceptual/chunking

julien-c

posted an update 15 days ago

Post

7575

After some heated discussion 🔥, we clarify our intent re. storage limits on the Hub

TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)

docs: https://huggingface.co./docs/hub/storage-limits

We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community 🔥

cc: @reach-vb @pierric @victor and the HF team

28 replies

·

clem

posted an update 23 days ago

Post

4084

Six predictions for AI in 2025 (and a review of how my 2024 predictions turned out):

- There will be the first major public protest related to AI
- A big company will see its market cap divided by two or more because of AI
- At least 100,000 personal AI robots will be pre-ordered
- China will start to lead the AI race (as a consequence of leading the open-source AI race).
- There will be big breakthroughs in AI for biology and chemistry.
- We will begin to see the economic and employment growth potential of AI, with 15M AI builders on Hugging Face.

How my predictions for 2024 turned out:

- A hyped AI company will go bankrupt or get acquired for a ridiculously low price
✅ (Inflexion, AdeptAI,...)

- Open-source LLMs will reach the level of the best closed-source LLMs
✅ with QwQ and dozens of others

- Big breakthroughs in AI for video, time-series, biology and chemistry
✅ for video 🔴for time-series, biology and chemistry

- We will talk much more about the cost (monetary and environmental) of AI
✅Monetary 🔴Environmental (😢)

- A popular media will be mostly AI-generated
✅ with NotebookLM by Google

- 10 millions AI builders on Hugging Face leading to no increase of unemployment
🔜currently 7M of AI builders on Hugging Face

4 replies

·

clem

posted an update 25 days ago

Post

4348

Hugging Face is becoming the best place to share the most viral AI apps with spaces.

Kolors Virtual Try-on just crossed 6,000,000 unique visitors & is now the #5 most popular space. Congrats to the Kwai Kolors team!

Kwai-Kolors/Kolors-Virtual-Try-On

2 replies

·

julien-c

posted an update 25 days ago

Post

2185

wow 😮

INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.

PrimeIntellect/INTELLECT-1-Instruct

victor

posted an update 26 days ago

Post

1778

Qwen/QwQ-32B-Preview shows us the future (and it's going to be exciting)...

I tested it against some really challenging reasoning prompts and the results are amazing 🤯.

Check this dataset for the results: victor/qwq-misguided-attention

2 replies

·

clem

posted an update 30 days ago

Post

1971

I've been in Brazil for 10 days now 🇧🇷🇧🇷🇧🇷

I've been surprised by the gap between the massive number of people interested in AI (chatgpt adoption is crazy here) and the relatively low number of real AI builders - aka people and companies building their own AI models, datasets and apps.

Lots of efforts needed across the world for everyone to participate, control and benefit this foundational technology, starting with open-source & multi-lingual AI, more access to GPUs & AI builder training for all!

victor

posted an update about 1 month ago

Post

2250

Perfect example of why Qwen/Qwen2.5-Coder-32B-Instruct is insane?

Introducing: AI Video Composer 🔥
huggingface-projects/ai-video-composer

Drag and drop your assets (images/videos/audios) to create any video you want using natural language!

It works by asking the model to output a valid FFMPEG and this can be quite complex but most of the time Qwen2.5-Coder-32B gets it right (that thing is a beast). It's an update of an old project made with GPT4 and it was almost impossible to make it work with open models back then (~1.5 years ago), but not anymore, let's go open weights 🚀.

victor

posted an update about 1 month ago

Post

1821

Qwen2.5-72B is now the default HuggingChat model.
This model is so good that you must try it! I often get better results on rephrasing with it than Sonnet or GPT-4!!

clem

posted an update about 1 month ago

Post

853

I'm in Belo Horizonte for a few days. Any HF community members in Brazil? What are the coolest orgs, models, datasets, spaces from here?

2 replies

·

clem

posted an update 2 months ago

Post

4435

This is no Woodstock AI but will be fun nonetheless haha. I’ll be hosting a live workshop with team members next week about the Enterprise Hugging Face hub.

1,000 spots available first-come first serve with some surprises during the stream!

You can register and add to your calendar here: https://streamyard.com/watch/JS2jHsUP3NDM

4 replies

·

clem

posted an update 2 months ago

Post

779

🕵️‍♂️ Let’s investigate NVIDIA's Llama-3.1-Nemotron-70B-Instruct-HF model performance - great analysis by @alozowski !

https://x.com/ailozovskaya/status/1847278827925291370

victor

posted an update 2 months ago

Post

1663

nvidia/Llama-3.1-Nemotron-70B-Instruct-HF is now available in HuggingChat if you want to try it!

https://huggingface.co./chat/models/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

clem

posted an update 2 months ago

Post

2049

Who's going to get to the most liked model on Hugging Face first: StabilityAI, Meta, Black Forest or someone else? The race is on!

2 replies

·

victor

posted an update 3 months ago

Post

2669

NEW - Inference Playground

Maybe like me you have always wanted a super easy way to compare llama3.2-1B vs. llama3.2-3B? or the same model with different temperatures?

Trying and comparing warm Inference API models has never been easier!
Just go to https://hf.co/playground, set your token and you're ready to go.
We'll keep improving, feedback welcome 😊

2 replies

·

clem

posted an update 3 months ago

Post

4161

Open-source AI creates healthy competition in a field where natural tendencies lead to extreme concentration of power. Imagine a world where only one or two companies could build software. This is the biggest risk and ethical challenge of them all IMO. Let's fight this!

3 replies

·

clem

posted an update 3 months ago

Post

2072

What are we thinking about MovieGen from Meta? Are the researchers on Hugging Face to be able to ask them questions?

The paper is here: https://ai.meta.com/static-resource/movie-gen-research-paper

clem

posted an update 3 months ago

Post

3709

Very few people realize that most of the successful AI startups got successful because they were focused on open science and open-source for at least their first few years. To name but a few, OpenAI (GPT, GPT2 was open-source), Runway & Stability (stable diffusion), Cohere, Mistral and of course Hugging Face!

The reasons are not just altruistic, it's also because sharing your science and your models pushes you to build AI faster (which is key in a fast-moving domain like AI), attracts the best scientists & engineers and generates much more visibility, usage and community contributions than if you were 100% closed-source. The same applies to big tech companies as we're seeing with Meta and Google!

More startups and companies should release research & open-source AI, it's not just good for the world but also increases their probability of success!