Hugging Face's logo

ONNXConfig for all

non-profit
Activity Feed Request to join this org

AI & ML interests

Make all hub models available for conversion to ONNX format.

Recent Activity

gagan3012  authored a paper about 1 month ago
DateLogicQA: Benchmarking Temporal Biases in Large Language Models
hazemessam  authored a paper 2 months ago
Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling
gagan3012  authored a paper 3 months ago
Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks
View all activity

OWG's activity

lewtun 
posted an update 14 days ago
view post
Post
3275
I was initially pretty sceptical about Meta's Coconut paper [1] because the largest perf gains were reported on toy linguistic problems. However, these results on machine translation are pretty impressive!

https://x.com/casper_hansen_/status/1875872309996855343

Together with the recent PRIME method [2] for scaling RL, reasoning for open models is looking pretty exciting for 2025!

[1] Training Large Language Models to Reason in a Continuous Latent Space (2412.06769)
[2] https://huggingface.co/blog/ganqu/prime
lewtun 
posted an update 20 days ago
view post
Post
2139
This paper ( HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs (2412.18925)) has a really interesting recipe for inducing o1-like behaviour in Llama models:

* Iteratively sample CoTs from the model, using a mix of different search strategies. This gives you something like Stream of Search via prompting.
* Verify correctness of each CoT using GPT-4o (needed because exact match doesn't work well in medicine where there are lots of aliases)
* Use GPT-4o to reformat the concatenated CoTs into a single stream that includes smooth transitions like "hmm, wait" etc that one sees in o1
* Use the resulting data for SFT & RL
* Use sparse rewards from GPT-4o to guide RL training. They find RL gives an average ~3 point boost across medical benchmarks and SFT on this data already gives a strong improvement.

Applying this strategy to other domains could be quite promising, provided the training data can be formulated with verifiable problems!
  • 1 reply
·
gagan3012 
authored a paper about 1 month ago
AtAndDev 
posted an update about 1 month ago
view post
Post
431
@s3nh Hey man check your discord! Got some news.
  • 4 replies
·
lewtun 
posted an update about 1 month ago
view post
Post
6746
We outperform Llama 70B with Llama 3B on hard math by scaling test-time compute 🔥

How? By combining step-wise reward models with tree search algorithms :)

We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think"

We're open sourcing the full recipe and sharing a detailed blog post.

In our blog post we cover:

📈 Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time.

🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets.

🧭 Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM

Here's the links:

- Blog post: HuggingFaceH4/blogpost-scaling-test-time-compute

- Code: https://github.com/huggingface/search-and-learn

Enjoy!
  • 2 replies
·
shivi 
authored 3 papers about 1 month ago
hazemessam 
authored a paper 2 months ago
louisbrulenaudet 
posted an update 2 months ago
view post
Post
1836
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
·
gagan3012 
authored a paper 3 months ago
louisbrulenaudet 
posted an update 3 months ago
view post
Post
1223
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
louisbrulenaudet 
posted an update 3 months ago
view post
Post
3120
🚨 I have $3,500 in Azure credits, including access to an H100 (96 Go), expiring on November 12, 2024.

I won’t be able to use it all myself, so I’m reaching out to the @huggingface community: Are there any open-source projets with data ready for some compute power?

Let’s collaborate and make the most of it together 🔗
·
louisbrulenaudet 
posted an update 4 months ago
view post
Post
2118
My biggest release of the year: a series of 7 specialized embedding models for information retrieval within tax documents, is now available for free on Hugging Face 🤗

These new models aim to offer an open source alternative for in-domain semantic search from large text corpora and will improve RAG systems and context addition for large language models.

Trained on more than 43 million tax tokens derived from semi-synthetic and raw-synthetic data, enriched by various methods (in particular MSFT's evol-instruct by @intfloat ), and corrected by humans, this project is the fruit of hundreds of hours of work and is the culmination of a global effort to open up legal technologies that has only just begun.

A big thank you to Microsoft for Startups for giving me access to state-of-the-art infrastructure to train these models, and to @julien-c , @clem 🤗, @thomwolf and the whole HF team for the inference endpoint API and the generous provision of Meta LLama-3.1-70B. Special thanks also to @tomaarsen for his invaluable advice on training embedding models and Loss functions ❤️

Models are available on my personal HF page, into the Lemone-embed collection: louisbrulenaudet/lemone-embed-66fdc24000df732b395df29b
  • 1 reply
·
louisbrulenaudet 
posted an update 4 months ago
view post
Post
2604
The Romulus model series has been released on Hugging Face, continually pre-trained on 34,864,949 tokens of French laws and intended to serve as a foundation for fine-tuning on labeled data 🤗

The training code, dataset and model weights are open and available free on HF and the training was based on H100 provided by Microsoft for Startups using Unsloth AI by @danielhanchen and @shimmyshimmer 🦥

Link to the base model: louisbrulenaudet/Romulus-cpt-Llama-3.1-8B-v0.1

Link to the instruct model: louisbrulenaudet/Romulus-cpt-Llama-3.1-8B-v0.1-Instruct

Link to the dataset: louisbrulenaudet/Romulus-cpt-fr

Please note that these models have not been aligned for the production of usable texts as they stand, and will certainly need to be refined for the desired tasks in order to produce satisfactory results.
  • 1 reply
·
louisbrulenaudet 
posted an update 4 months ago
view post
Post
1576
An example of the application of LegalKit is the production of knowledge graphs, here is a demo Space 🔗

With the update of the French legal code data model uploaded to 🤗 and the introduction of a column dedicated to HTML text, it's now easy to extract links between different articles and produce complex graphs with just a few lines of Python.

This simplified demo highlights the ease of implementation and creative potential, and enables the generation of complete data sets, although requiring a powerful graphics card for display. The framework used for the moment is D3.js, but perhaps other solutions are possible. I'd be delighted to hear your suggestions, and look forward to hearing from the community.

Link to the 🤗 Space: louisbrulenaudet/legalkit-knowledge-graph
  • 2 replies
·
Niansuh 
posted an update 5 months ago
view post
Post
2640
Plugins in NiansuhAI

Plugin Names:
1. WebSearch: Searches the web using search engines.
2. Calculator: Evaluates mathematical expressions, extending the base Tool class.
3. WebBrowser: Extracts and summarizes information from web pages.
4. Wikipedia: Retrieves information from Wikipedia using its API.
5. Arxiv: Searches and fetches article information from Arxiv.
6. WolframAlphaTool: Provides answers on math, science, technology, culture, society, and everyday life.

These plugins currently support the GPT-4O-2024-08-06 model, which also supports image analysis.

Try it now: https://huggingface.co/spaces/NiansuhAI/chat

Similar to: https://hf.co/chat
louisbrulenaudet 
posted an update 5 months ago
view post
Post
2026
Understanding the json format response with HF's Serverless Inference API 🤗

As it stands, there seems to be an inconsistency with the OpenAI documentation on the question of implementing the JSON response format using the InferenceClient completion API.

After investigating the InferenceClient source code, I share the official solution using a JSON Schema. This consolidates the structure of the response and simplifies parsing as part of an automated process for extracting metadata, information:
from huggingface_hub import InferenceClient

client = InferenceClient("meta-llama/Meta-Llama-3-70B-Instruct")

messages = [
    {
        "role": "user",
        "content": "I saw a puppy a cat and a raccoon during my bike ride in the park. What did I saw and when?",
    },
]

response_format = {
    "type": "json",
    "value": {
        "properties": {
            "location": {"type": "string"},
            "activity": {"type": "string"},
            "animals_seen": {"type": "integer", "minimum": 1, "maximum": 5},
            "animals": {"type": "array", "items": {"type": "string"}},
        },
        "required": ["location", "activity", "animals_seen", "animals"],
    },
}

response = client.chat_completion(
    messages=messages,
    response_format=response_format,
    max_tokens=500,
)

print(response.choices[0].message.content)

As a reminder, json mode is activated with the OpenAI client as follows:
response = client.chat.completions.create(
     model="gpt-3.5-turbo-0125",
     messages=[...],
     response_format={"type": "json_object"}
)

One question remains unanswered, however, and will perhaps be answered by the community: it seems that an incompatibility persists for list of dictionaries generation, and currently, the production of simple dictionaries seems to be the only functional option.
  • 2 replies
·
louisbrulenaudet 
posted an update 5 months ago
view post
Post
2762
🚀 RAGoon is now available on PyPI, GitHub, and as a Space on Hugging Face for batched embeddings generation 🤗

RAGoon is a set of NLP utilities for multi-model embedding production, high-dimensional vector visualization, and aims to improve language model performance by providing contextually relevant information through search-based querying, web scraping and data augmentation techniques.

At this stage, 5 major classes are available via RAGoon to facilitate:
- the production of chain embeddings for several models to simplify a continuous deployment process;
- production of LLM requests for web querying and content retrieval via the Google API;
- recursive chunking via tokens;
- data visualization and the function to load embeddings from a FAISS index, reduce their dimensionality using PCA and/or t-SNE, and visualize them in an interactive 3D graph;
- the creation of binary indexes for search with scalar (int8) rescoring.

Link to GitHub: https://github.com/louisbrulenaudet/ragoon
Link to the 🤗 Space: louisbrulenaudet/ragoon
Artples 
posted an update 6 months ago
view post
Post
2475
Looking for a combination of speed and quality? Look no further! I've created a space that merges Open WebUI's excellent interface and features with the lightning-fast performance of the Groq API. Experience top-tier models in no time. Try it out for free here:
L-AI/groq-chat

"A big thank you to Groq for providing their fantastic API at no cost!"