Hugging Face – Posts

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

All HF Hub posts

Nitral-AI

posted an update 2 days ago

Post

2525

That moment when you spend 5 days up babysitting trains, only for colab pro + to randomly disconnect the environment at every chance with 0 error indication of any kind (it just disconnects without an error). Nuke the session from the interface, but continue to eat my colab credits while it reports to wandb. 0 way of saving the models when this happens since it nukes the code preset up to auto-execute. And since the sessions 'exist' but also at the same time doesn't exist i cant close it. And have to wait till they auto timeout after 24hrs. Guess, i won't be using colab for 'quick' test trains anymore. Thanks google for scheming the very little model training budget i had for the month.

3 replies

merve

posted an update about 19 hours ago

Post

953

What a beginning to this year in open ML 🤠
Let's unwrap! merve/jan-10-releases-677fe34177759de0edfc9714

Multimodal 🖼️
> ByteDance released SA2VA: a family of vision LMs that can take image, video, text and visual prompts
> moondream2 is out with new capabilities like outputting structured data and gaze detection!
> Dataset: Alibaba DAMO lab released multimodal textbook — 22k hours worth of samples from instruction videos 🤯
> Dataset: SciCap captioning on scientific documents benchmark dataset is released along with the challenge!

LLMs 💬
> Microsoft released Phi-4, sota open-source 14B language model 🔥
> Dolphin is back with Dolphin 3.0 Llama 3.1 8B 🐬🐬
> Prime-RL released Eurus-2-7B-PRIME a new language model trained using PRIME alignment
> SmallThinker-3B is a new small reasoning LM based on Owen2.5-3B-Instruct 💭
> Dataset: QWQ-LONGCOT-500K is the dataset used to train SmallThinker, generated using QwQ-32B-preview 📕
> Dataset: @cfahlgren1 released React Code Instructions: a dataset of code instruction-code pairs 📕
> Dataset: Qwen team is on the roll, they just released CodeElo, a dataset of code preferences 👩🏻‍💻

Embeddings 🔖
> @MoritzLaurer released zero-shot version of ModernBERT large 👏
> KaLM is a new family of performant multilingual embedding models with MIT license built using Qwen2-0.5B

Image/Video Generation ⏯️
> NVIDIA released Cosmos, a new family of diffusion/autoregressive World Foundation Models generating worlds from images, videos and texts 🔥
> Adobe released TransPixar: a new text-to-video model that can generate assets with transparent backgrounds (a first!)
> Dataset: fal released cosmos-openvid-1m Cosmos-tokenized OpenVid-1M with samples from OpenVid-1M

Others
> Prior Labs released TabPFNv2, the best tabular transformer is out for classification and regression
> Metagene-1 is a new RNA language model that can be used for pathogen detection, zero-shot embedding and genome understanding

prithivMLmods

posted an update 2 days ago

Post

2143

200+ f{🤗} on Stranger Zone! [ https://huggingface.co/strangerzonehf ]

❤️‍🔥Stranger Zone's MidJourney Mix Model Adapter is trending on the Very Model Page, with over 45,000+ downloads. Additionally, the Super Realism Model Adapter has over 52,000+ downloads, remains the top two adapter on Stranger Zone!
strangerzonehf/Flux-Midjourney-Mix2-LoRA, strangerzonehf/Flux-Super-Realism-LoRA

👽Try Demo: prithivMLmods/FLUX-LoRA-DLC

📦Most Recent Adapters to Check Out :
+ Ctoon : strangerzonehf/Ctoon-Plus-Plus
+ Cardboard : strangerzonehf/Flux-Cardboard-Art-LoRA
+ Claude Art : strangerzonehf/Flux-Claude-Art
+ Flay Lay : strangerzonehf/Flux-FlatLay-LoRA
+ Smiley Portrait : strangerzonehf/Flux-Smiley-Portrait-LoRA

🤗Thanks for Community & OPEN SOURCEEE !!

6 replies

hexgrad

posted an update 5 days ago

Post

4623

📣 Looking for labeled, high-quality synthetic audio/TTS data 📣 Have you been or are you currently calling API endpoints from OpenAI, ElevenLabs, etc? Do you have labeled audio data sitting around gathering dust? Let's talk! Join https://discord.gg/QuGxSWBfQy or comment down below.

If your data exceeds quantity & quality thresholds and is approved into the next hexgrad/Kokoro-82M training mix, and you permissively DM me the data under an effective Apache license, then I will DM back the corresponding voicepacks for YOUR data if/when the next Apache-licensed Kokoro base model drops.

What does this mean? If you've been calling closed-source TTS or audio API endpoints to:
- Build voice agents
- Make long-form audio, like audiobooks or podcasts
- Handle customer support, etc
Then YOU can contribute to the training mix and get useful artifacts in return. ❤️

More details at hexgrad/Kokoro-82M#21

13 replies

davanstrien

posted an update about 24 hours ago

Post

863

The data-is-better-together/fineweb-c dataset is growing!

This week a few more languages have got 1,000 annotations for the educational quality of data from HuggingFaceFW/fineweb-2.

Why should you care?

The quality of pre-training data can have a big impact on the performance of downstream language models trained on that data ( HuggingFaceFW/blogpost-fineweb-v1).

Being able to filter by educational quality is on way of improving the quality of the data you use for training an LLM. Very importantly this approach can also reduce the amount of data needed for pertaining.

Why not use an LLM?

LLMs can be used to annotate educational quality for a subset of data. This data can then be used to train a smaller encoder only model to label the full dataset. However, this may not work well for languages outside of english. This is where fineweb-c (community) comes in.

The community is annotating the educational quality of fineweb2 data. Currently 114 languages have some annotations. These annotations will enable a number of things:

- Evaluate whether an LLM can label the educational quality for texts in that language well
- Directly be used for training quality classifiers
- Help discover other rules and huerisitcs for refining fineweb2 further for different languages.

This week the following languages where done:

Swedish thanks to: @Lauler @AntonVic @ohallstrom @bjarlestam @menbom @Ekgren @apsod

Ukrainian thanks to: @hannayukhymenko @robinhad @realPivo @RabotiahovDmytro @reciprocate

Assamese thanks to: @moyoor97 @Arpanjyoti @nawaf-helmi123 @pahigogoi1 @aelhence @kishorekashyap

Want to learn more: https://huggingface.co/blog/davanstrien/fineweb2-community

Contribute yourself here: data-is-better-together/fineweb-c

1 reply

merve

posted an update 2 days ago

Post

1405

ByteDance just dropped SA2VA: a new family of vision LMs combining Qwen2VL/InternVL and SAM2 with MIT license 💗 ByteDance/sa2va-model-zoo-677e3084d71b5f108d00e093

> The models are capable of tasks involving vision-language understanding and visual referrals (referring segmentation) both for images and videos ⏯️

> The models come in 1B, 4B and 8B and are based on InternVL2.5 for base architecture and Qwen2, Qwen2.5 and InternLM2 for language model part (depending on the checkpoint)

> The model is very interesting, it has different encoders for different modalities each (visual prompt, text prompt, image and video) then it concatenates these to feed into LLM 💬

the output segmentation tokens are passed to SAM2, to sort of match text (captions or semantic classes) to masks ⤵️

> Their annotation pipeline is also interesting, they seems to use two open large vision LMs to refine the annotations, and have different levels of descriptions to provide consistency.

1 reply

Severian

posted an update 3 days ago

Post

3610

Interesting Solution to the Problem of Misguided Attention

So I've been fascinated by the problem of Misguided Attention for a few weeks. I am trying to build an inference algorithm to help LLMs address that issue; but in the process, I found a cool short-term fix I call "Mindful Attention" using just prompt-engineering.

Have you ever thought about how our brains filter reality through layers of past experiences, concepts, and mental images? For example, when you look at an oak tree, are you truly seeing that oak tree in all its unique details, or are you overlaying it with a generalized idea of "oak tree"? This phenomenon inspired the new approach.

LLMs often fall into a similar trap, hence the Misguided Attention problem. They process input not as it’s uniquely presented but through patterns and templates they’ve seen before. This leads to responses that can feel "off," like missing the point of a carefully crafted prompt or defaulting to familiar but irrelevant solutions.

I wanted to address this head-on by encouraging LLMs to slow down, focus, and engage directly with the input—free of assumptions. This is the core of the Mindful Attention Directive, a prompt designed to steer models away from over-generalization and back into the moment.

You can read more about the broader issue here: https://github.com/cpldcpu/MisguidedAttention

And if you want to try this mindful approach in action, check out the LLM I’ve set up for testing: https://hf.co/chat/assistant/677e7ebcb0f26b87340f032e. It works about 80% of the time to counteract these issues, and the results are pretty cool.

I'll add the Gist with the full prompt. I admit, it is quite verbose but it's the most effective one I have landed on yet. I am working on a smaller version that can be appended to any System Prompt to harness the Mindful Attention. Feel free to experiment to find a better version for the community!

Here is the Gist: https://gist.github.com/severian42/6dd96a94e546a38642278aeb4537cfb3

MoritzLaurer

posted an update 2 days ago

Post

1372

The TRL v0.13 release is 🔥! My highlight are the new process reward trainer to train models similar to o1 and tool call support:

🧠 Process reward trainer: Enables training of Process-supervised Reward Models (PRMs), which reward the quality of intermediate steps, promoting structured reasoning. Perfect for tasks like stepwise reasoning.

🔀 Model merging: A new callback leverages mergekit to merge models during training, improving performance by blending reference and policy models - optionally pushing merged models to the Hugging Face Hub.

🛠️ Tool call support: TRL preprocessing now supports tool integration, laying the groundwork for agent fine-tuning with examples like dynamic temperature fetching in prompts.

⚖️ Mixture of judges: The new AllTrueJudge combines decisions from multiple binary judges for more nuanced evaluation.

Read the release notes and other resources here 👇
Release: https://github.com/huggingface/trl/releases/tag/v0.13.0
Mergekit: https://github.com/arcee-ai/mergekit
Mixture of judges paper: The Perfect Blend: Redefining RLHF with Mixture of Judges (2409.20370)

danielhanchen

posted an update about 12 hours ago

Post

334

We fixed many bugs in Phi-4 & uploaded fixed GGUF + 4-bit versions! ✨

Our fixed versions are even higher on the Open LLM Leaderboard than Microsoft's!

GGUFs: unsloth/phi-4-GGUF
Dynamic 4-bit: unsloth/phi-4-unsloth-bnb-4bit

You can also now finetune Phi-4 for free on Colab: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_4-Conversational.ipynb

Read our blogpost for more details on bug fixes etc: https://unsloth.ai/blog/phi4

CultriX

posted an update about 17 hours ago

Post

517

# Space for Multi-Agent Workflows using AutoGen

Hi all, I created this "AutoGen Multi-Agent Workflow" space that allows you to experiment with multi-agent workflows.

By default, it allows code generation with built-in quality control and automatic documentation generation. It achieves this by leveraging multiple AI agents working together to produce high-quality code snippets, ensuring they meet the specified requirements.

In addition to the default, the space allows users to set custom system messages for each assistant, potentially completely changing the workflow.

# Workflow Steps
1. User Input:
- The user defines a prompt, such as "Write a random password generator using python."
- Outcome: A clear task for the primary assistant to accomplish.

2. Primary Assistant Work:
- The primary assistant begins working on the provided prompt.
It generates an initial code snippet based on the user's request.
- Outcome: An initial proposal for the requested code.

3. Critic Feedback:
- The critic reviews the generated code provides feedback or (if the output meets the criteria), broadcasts the APPROVED message.
(This process repeats until the output is APPROVED or 10 messages have been exchanged).
- Outcome: A revised Python function that incorporates the critic's feedback.

4. Documentation Generation:
- Once the code is approved, it is passed to a documentation assistant.
The documentation assistant generates a concise documentation for the final code.
- Outcome: A short documentation including function description, parameters, and return values.

Enjoy!
CultriX/AutoGen-MultiAgent-Example

3 replies

Recently active users