louisbrulenaudet (Louis Brulé Naudet)

reacted to m-ric's post with 🚀 11 days ago

Post

2413

𝗪𝗲'𝘃𝗲 𝗷𝘂𝘀𝘁 𝗿𝗲𝗹𝗲𝗮𝘀𝗲𝗱 𝘀𝗺𝗼𝗹𝗮𝗴𝗲𝗻𝘁𝘀 𝘃𝟭.𝟯.𝟬 🚀, and it comes with a major feature: you can now log agent runs using OpenTelemetry to inspect them afterwards! 📊

This interactive format is IMO much easier to inspect big multi-step runs than endless console logs.

The setup is very easy, in a few lines of code.

Find a tutorial here 👉 https://huggingface.co/docs/smolagents/tutorials/inspect_runs

4 replies

·

reacted to MonsterMMORPG's post with 🔥 13 days ago

Post

4426

It is now possible to generate 16 Megapixel (4096x4096) raw images with SANA 4K model using under 8GB VRAM, 4 Megapixel (2048x2048) images using under 6GB VRAM, and 1 Megapixel (1024x1024) images using under 4GB VRAM thanks to new optimizations

13 January 2024 Update

Installers : https://www.patreon.com/posts/from-nvidia-labs-116474081

New 4K Tutorial Video : https://youtu.be/GjENQfHF4W8

Now the APP will use Diffusers Pipeline and it has huge VRAM optimizations

You need to reinstall

The models will be downloaded into your Hugging Face cache folder when you first time generate something

How to Get Installation Logs and How to Change Hugging Face Cache Folder :
https://www.patreon.com/posts/108419878

Please make a fresh install

When you enable all 4 optimizations the VRAM usages are like below

Make sure shared VRAM is enabled because initial loading of the model need more VRAM

Enable VAE Tiling + Enable VAE Slicing + Enable Model CPU Offload +
Enable Sequential CPU Offload

1K (1024x1024) : 4 GB GPUs
2K (2048x2048) : 6 GB GPUs
4K (4096x4096) : 8 GB GPUs

Still in any case may work on your GPU test it

Just Enable VAE Tiling + Enable Model CPU Offload works great in many cases

All below attached images are generated via SANA 4K model, they are RAW and their resolution is 5376x3072

Official repo page : https://github.com/NVlabs/Sana

2 replies

·

reacted to anakin87's post with ❤️ about 2 months ago

Post

1650

Tulu 3 SFT Mixture by AllenAI is a massive, good, multilingual dataset for fine-tuning Language Models.

Unfortunately, it was missing the "language" column.

I added it using the good old fastText.

Check out the dataset here 👉 anakin87/tulu-3-sft-mixture-with-language

1 reply

·

reacted to Jaward's post with 🧠 about 2 months ago

Post

2432

Implements compute-efficient DeepPCR algorithm which parallelizes sequential operations thus speeding up inference and training of neural networks. DeepPCR can significantly reduce the time complexity in operations such as denoising in latent diffusion space from O(L) to O(log2 L).

Code: https://github.com/Jaykef/ai-algorithms/blob/main/deep_pcr.ipynb

reacted to prithivMLmods's post with 🔥 2 months ago

Post

3302

HF Posts Receipts 🏆🚀

[ HF POSTS RECEIPT ] : prithivMLmods/HF-POSTS-RECEIPT

🥠The one thing that needs to be remembered is the 'username'.

🥠And yeah, thank you, @maxiw , for creating the awesome dataset and sharing them here! 🙌

🥠[ Dataset ] : maxiw/hf-posts

.
.
.
@prithivMLmods

reacted to clem's post with 🚀 2 months ago

Post

1991

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!

posted an update 2 months ago

Post

1879

I’ve published a new dataset to simplify model merging 🤗

This dataset facilitates the search for compatible architectures for model merging with @arcee_ai’s mergekit, streamlining the automation of high-performance merge searches 📖

Dataset : louisbrulenaudet/mergekit-configs

1 reply

·

reacted to m-ric's post with 🔥 3 months ago

Post

3182

𝗤𝘄𝗲𝗻𝟮.𝟱-𝗖𝗼𝗱𝗲𝗿-𝟯𝟮𝗕: 𝗻𝗲𝘄 𝗯𝗲𝘀𝘁-𝗶𝗻-𝗰𝗹𝗮𝘀𝘀 𝗼𝗽𝗲𝗻 𝗰𝗼𝗱𝗶𝗻𝗴 𝗺𝗼𝗱𝗲𝗹, 𝗯𝗲𝗮𝘁𝘀 𝗚𝗣𝗧-𝟰𝗼 𝗼𝗻 𝗺𝗼𝘀𝘁 𝗰𝗼𝗱𝗶𝗻𝗴 𝗯𝗲𝗻𝗰𝗵𝗺𝗮𝗿𝗸𝘀!💥

💪 It's the first time Open-Source coding model of this size class that clearly matches GPT-4o's coding capabilities!

✨ Completes the previous two Qwen 2.5 Coder release with 4 new size: 0.5B, 3B, 14B, 32B
📚 Support long context up to 128K (for the 14B and 32B models)
✅ Drop-in replacement to GPT-4o as a coding assistant on Cursor or for Artifacts!
🤗 Models available right now on the Hub, under Apache 2.0 license!

They have setup a crazy Artifacts demo, you should go have a look!
👉 Qwen/Qwen2.5-Coder-Artifacts

reacted to m-ric's post with 👀 3 months ago

Post

2377

A non-Instruct LLM assistant is mostly useless. 🧐

Since it's mostly a model trained to complete text, when you ask it a question like "What to do during a stopover in Paris?", it can just go on and on adding more details to your question instead of answering, which would be valid to complete text from its training corpus, but not to answer questions.

➡️ So the post-training stage includes an important Instruction tuning step where you teach your model how to be useful : answer questions, be concise, be polite... RLHF is a well known technique for this.

For people interested to understand how this step works, the folks at Adaptive ML have made a great guide!

Read it here 👉 https://www.adaptive-ml.com/post/from-zero-to-ppo

reacted to prithivMLmods's post with 🤝 3 months ago

Post

5771

New Style, New Mix, New Drop 🧤

🧨Flux LoRA DLC: prithivMLmods/FLUX-LoRA-DLC

🎆Glowing-Body: prithivMLmods/Glowing-Body-Flux-LoRA
🎆Electric-Blue: prithivMLmods/Electric-Blue-Flux-LoRA
🎆Intense-Red: prithivMLmods/Intense-Red-Flux-LoRA
🎆Clouds-Illusion: prithivMLmods/Clouds-Illusion-Flux-LoRA
🎆Digital-Yellow: prithivMLmods/Digital-Yellow-Flux-LoRA

🧨Flux LoRA Collection: prithivMLmods/flux-lora-collections-66dd5908be2206cfaa8519be

.
.
.
@prithivMLmods

reacted to m-ric's post with 🚀 3 months ago

Post

1636

𝗔𝗻𝗱𝗿𝗼𝗶𝗱𝗟𝗮𝗯: 𝗙𝗶𝗿𝘀𝘁 𝗲𝘃𝗲𝗿 𝘀𝘆𝘀𝘁𝗲𝗺𝗮𝘁𝗶𝗰 𝗯𝗲𝗻𝗰𝗵𝗺𝗮𝗿𝗸 𝗳𝗼𝗿 𝗔𝗻𝗱𝗿𝗼𝗶𝗱 𝗺𝗼𝗯𝗶𝗹𝗲 𝗮𝗴𝗲𝗻𝘁𝘀 𝘀𝗵𝗼𝘄𝘀 𝘁𝗵𝗮𝘁 𝘀𝗺𝗮𝗹𝗹, 𝗳𝗶𝗻𝗲-𝘁𝘂𝗻𝗲𝗱 𝗼𝗽𝗲𝗻 𝗺𝗼𝗱𝗲𝗹𝘀 𝗰𝗮𝗻 𝗽𝗼𝘄𝗲𝗿 𝗮 𝗝𝗔𝗥𝗩𝗜𝗦 𝘀𝘆𝘀𝘁𝗲𝗺 𝗼𝗻 𝘆𝗼𝘂𝗿 𝘀𝗺𝗮𝗿𝘁𝗽𝗵𝗼𝗻𝗲 📱🔥

A team from Tsinghua University just released AndroidLab, the first systematic framework to evaluate and train Android mobile agents that works with both text-only and multimodal models.

They show that fine-tuning small open-source models can significantly boost performance, matching that of much bigger closed models like GPT-4o.

The team built:

📊 A reproducible benchmark with 138 tasks across 9 apps to evaluate mobile agents systematically

📝📱 A framework supporting both text-only (via XML) and visual (via marked screenshots) interfaces

✅ An instruction dataset of 10.5k operation traces for training mobile agents

Key insights:

- 📈 Fine-tuning improves performance BY A LOT: Open-source model Llama-3.1-8B improves from 2% to 24% success rate after training, nearly reaching GPT-4o performance although it’s much smaller
- ⚙️ Text-only agents match multimodal ones: XML-based agents achieve similar performance to screenshot-based multimodal agents.

Read their paper here 👉 AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2410.24024)

reacted to abhishek's post with 🔥 3 months ago

Post

5784

INTRODUCING Hugging Face AutoTrain Client 🔥
Fine-tuning models got even easier!!!!
Now you can fine-tune SOTA models on all compatible dataset-model pairs on Hugging Face Hub using Python on Hugging Face Servers. Choose from a number of GPU flavors, millions of models and dataset pairs and 10+ tasks 🤗

To try, install autotrain-advanced using pip. You can ignore dependencies and install without --no-deps and then you'd need to install some dependencies by hand.

"pip install autotrain-advanced"

Github repo: https://github.com/huggingface/autotrain-advanced

6 replies

·

reacted to prithivMLmods's post with ❤️ 3 months ago

Post

4911

Style flo : : 🎉🤗

{ Try Now on Flux LoRA DLC ⛵ } : prithivMLmods/FLUX-LoRA-DLC

-- Undersea
{ Red Fluid } : prithivMLmods/Red-Undersea-Flux-LoRA

-- 3D Realmix
{ 3D Portrait Render } : prithivMLmods/3D-Render-Flux-LoRA

-- Pop
{ Yellow Pop } : prithivMLmods/Yellow-Pop-Flux-Dev-LoRA

-- Grid
{ Purple Grid } : prithivMLmods/Purple-Grid-Flux-LoRA

{ collections : : }

🚀 Flux LoRA :
prithivMLmods/flux-lora-collections-66dd5908be2206cfaa8519be

🚀Collection zero: prithivMLmods/collection-zero-and-demo-recently-updated-65e48a7dd8212873836ceca2

.
.
@prithivMLmods 🧨

reacted to yagilb's post with 👀 3 months ago

Post

3125

🫵👾 LM Studio is hiring engineers who know the ins and outs of NodeJS & want to work on local LLMs.

Know anyone who might be interested?

Apply here: https://docs.google.com/forms/d/e/1FAIpQLSc_786-_i_q4fo5ESqYnNyjIH0B5Rs45QIwejd_NV5AjNDZ7A/viewform

reacted to singhsidhukuldeep's post with 👀 3 months ago

Post

2104

Exciting Research Alert: Revolutionizing Dense Passage Retrieval with Entailment Tuning!

The good folks at HKUST have developed a novel approach that significantly improves information retrieval by leveraging natural language inference.

The entailment tuning approach consists of several key steps to enhance dense passage retrieval performance.

Data Preparation
- Convert questions into existence claims using rule-based transformations.
- Combine retrieval data with NLI data from SNLI and MNLI datasets.
- Unify the format of both data types using a consistent prompting framework.

Entailment Tuning Process
- Initialize the model using pre-trained language models like BERT or RoBERTa.
- Apply aggressive masking (β=0.8) specifically to the hypothesis components while preserving premise information.
- Train the model to predict the masked hypothesis tokens from the premise content.
- Run the training for 10 epochs using 8 GPUs, taking approximately 1.5-3.5 hours.

Training Arguments for Entailment Tuning (Yes! They Shared Them)
- Use a learning rate of 2e-5 with 100 warmup steps.
- Set batch size to 128.
- Apply weight decay of 0.01.
- Utilize the Adam optimizer with beta values (0.9, 0.999).
- Maintain maximum gradient norm at 1.0.

Deployment
- Index passages using FAISS for efficient retrieval.
- Shard vector store across multiple GPUs.
- Enable sub-millisecond retrieval of the top-100 passages per query.

Integration with Existing Systems
- Insert entailment tuning between pre-training and fine-tuning stages.
- Maintain compatibility with current dense retrieval methods.
- Preserve existing contrastive learning approaches during fine-tuning.

Simple, intuitive, and effective!

This advancement significantly improves the quality of retrieved passages for question-answering systems and retrieval-augmented generation tasks.

reacted to reach-vb's post with 🚀 3 months ago

Post

3010

Smol models ftw! AMD released AMD OLMo 1B - beats OpenELM, tiny llama on MT Bench, Alpaca Eval - Apache 2.0 licensed 🔥

> Trained with 1.3 trillion (dolma 1.7) tokens on 16 nodes, each with 4 MI250 GPUs

> Three checkpoints:

- AMD OLMo 1B: Pre-trained model
- AMD OLMo 1B SFT: Supervised fine-tuned on Tulu V2, OpenHermes-2.5, WebInstructSub, and Code-Feedback datasets
- AMD OLMo 1B SFT DPO: Aligned with human preferences using Direct Preference Optimization (DPO) on UltraFeedback dataset

Key Insights:
> Pre-trained with less than half the tokens of OLMo-1B
> Post-training steps include two-phase SFT and DPO alignment
> Data for SFT:
- Phase 1: Tulu V2
- Phase 2: OpenHermes-2.5, WebInstructSub, and Code-Feedback

> Model checkpoints on the Hub & Integrated with Transformers ⚡️

Congratulations & kudos to AMD on a brilliant smol model release! 🤗

amd/amd-olmo-6723e7d04a49116d8ec95070

replied to their post 3 months ago

Hello,

Thank you for reaching out. I'm interested in learning more about its potential applications and dataset specifics. To ensure we’re aligned on objectives and timelines, would you mind detailing a bit further on the following in the Tally form? (https://tally.so/r/w2xe0A)

Project Goals: What are the primary objectives for your model, and how do you envision deploying it?
Data and Compute Requirements: Could you outline the volume and nature of data you'd like to process and any specific requirements for H100 access?
Finetuning Method: I'd be interested to hear more about your finetuning approach. Do you have a plan for iterations or specific benchmarks in mind?

Please submit your responses via the form to streamline our discussion. Once we have the foundational details clarified, we can determine the next steps and see how best to leverage the Azure credits together.

Looking forward to exploring the possibilities.

Best regards, Louis

replied to their post 3 months ago

Hello @Siddartha10 ,

Thank you for reaching out! I'm excited to hear about your work and the potential for collaboration.

To help assess how best to support your project, could you please share a bit more detail? Specifically:

Project Overview: A brief description of your project and its objectives.
Data Preparedness: Whether your data is ready for immediate use and the nature of this data.
Expected Outcomes: The goals or deliverables you anticipate achieving with this additional compute power.

Feel free to submit your details via this form Tally form (https://tally.so/r/w2xe0A) so we can proceed efficiently.

Looking forward to learning more about your project and potentially collaborating!

Best regards,
Louis

replied to their post 3 months ago

Hi @Pankaj8922 ,

Thank you for reaching out and sharing your project concept! For this collaboration, I'm specifically seeking projects that already have data prepared and ready for immediate use, as the Azure credits are limited and focused on applications that can be initiated without additional data generation steps.

If you have any projects with data fully prepared, feel free to submit details through the form here: https://tally.so/r/w2xe0A.

Best of luck with your synthetic dataset project!

posted an update 3 months ago

Post

1262

Introducing Lemone-router, a series of classification models designed to produce an optimal multi-agent system for different branches of tax law.

Trained on a base of 49k lines comprising a set of synthetic questions generated by GPT-4 Turbo and Llama 3.1 70B, which have been further refined through evol-instruction tuning and manual curation and authority documents, these models are based on an 8-category decomposition of the classification scheme derived from the Bulletin officiel des finances publiques - impôts :

label2id = {
    "Bénéfices professionnels": 0,
    "Contrôle et contentieux": 1,
    "Dispositifs transversaux": 2,
    "Fiscalité des entreprises": 3,
    "Patrimoine et enregistrement": 4,
    "Revenus particuliers": 5,
    "Revenus patrimoniaux": 6,
    "Taxes sur la consommation": 7
}
	
id2label = {
    0: "Bénéfices professionnels",
    1: "Contrôle et contentieux",
    2: "Dispositifs transversaux",
    3: "Fiscalité des entreprises",
    4: "Patrimoine et enregistrement",
    5: "Revenus particuliers",
    6: "Revenus patrimoniaux",
    7: "Taxes sur la consommation"
}

It achieves the following results on the evaluation set:
- Loss: 0.4734
- Accuracy: 0.9191

Link to the collection: louisbrulenaudet/lemone-router-671cce21d6410f3570514762

Louis Brulé Naudet PRO

AI & ML interests

Recent Activity

Organizations

louisbrulenaudet's activity