Our Transformers Code Agent beats the GAIA benchmark!
•
45
Aymeric Roucher
m-ric
AI & ML interests
MLE at Hugging Face 🤗
LLMs, Agents, RAG, Multimodal.
Articles
Organizations
Posts
44
Post
674
Transformers v4.45.0 released: includes a lightning-fast method to build tools! ⚡️
During user research with colleagues @MoritzLaurer and @Jofthomas , we discovered that the class definition currently in used to define a Tool in
➡️ So I’ve made an easier way to build tools: just make a function with type hints + a docstring, and add a @tool decorator in front.
✅ Voilà, you’re good to go!
Read all about it in the new doc here: https://huggingface.co/docs/transformers/main/en/agents#create-a-new-tool
And don’t hesitate to give feedback, I’m all ears! 🤗
During user research with colleagues @MoritzLaurer and @Jofthomas , we discovered that the class definition currently in used to define a Tool in
transformers.agents is a bit tedious to use, because it goes in great detail.➡️ So I’ve made an easier way to build tools: just make a function with type hints + a docstring, and add a @tool decorator in front.
✅ Voilà, you’re good to go!
Read all about it in the new doc here: https://huggingface.co/docs/transformers/main/en/agents#create-a-new-tool
And don’t hesitate to give feedback, I’m all ears! 🤗
Post
2836
🌎 𝐓𝐡𝐞 𝐟𝐢𝐫𝐬𝐭 𝐞𝐯𝐞𝐫 𝐅𝐨𝐮𝐧𝐝𝐚𝐭𝐢𝐨𝐧 𝐰𝐞𝐚𝐭𝐡𝐞𝐫 𝐦𝐨𝐝𝐞𝐥: 𝐏𝐫𝐢𝐭𝐡𝐯𝐢 𝐖𝐱𝐂 𝐞𝐧𝐚𝐛𝐥𝐞𝐬 𝐥𝐢𝐟𝐞-𝐬𝐚𝐯𝐢𝐧𝐠 𝐰𝐞𝐚𝐭𝐡𝐞𝐫 𝐩𝐫𝐞𝐝𝐢𝐜𝐭𝐢𝐨𝐧𝐬
Hurricane Katrina killed hundreds of people as it made landfall on New Orleans in 2005 - many of these deaths could have been avoided if alerts had been given one day earlier. Accurate weather forecasts are really life-saving.
🔥 Now, NASA and IBM just dropped a game-changing new model: the first ever foundation model for weather! This means, it's the first time we have a generalist model not restricted to one task, but able to predict 160 weather variables!
Prithvi WxC (Prithvi, “पृथ्वी”, is the Sanskrit name for Earth) - is a 2.3 billion parameter model, with an architecture close to previous vision transformers like Hiera.
💡 But it comes with some important tweaks: under the hood, Prithvi WxC uses a clever transformer-based architecture with 25 encoder and 5 decoder blocks. It alternates between "local" and "global" attention to capture both regional and global weather patterns.
𝗞𝗲𝘆 𝗶𝗻𝘀𝗶𝗴𝗵𝘁𝘀:
🔮 Nails short-term forecasts - Prithvi WxC crushed it on 6-12 hour predictions, even outperforming some traditional numerical weather models
🌀 Tracks hurricanes like a champ - For Hurricane Ida, it predicted the landfall location within 5 km (vs 20+ km errors from other AI models), which is a huge progress!
🔍 6x downscaling power - Can zoom in on weather data to 6x higher resolution with 4x lower error than basic methods
🌊 Models elusive gravity waves - Accurately simulates these crucial but hard-to-capture atmospheric oscillations
As climate change intensifies, tools like Prithvi WxC will become more and more crucial to avoid disasters!
Announcement post 👉 https://newsroom.ibm.com/2024-09-23-ibm-and-nasa-release-open-source-ai-model-on-hugging-face-for-weather-and-climate-applications
Model on the Hub 👉 https://huggingface.co/Prithvi-WxC
Thank you @clem for highlighting it!
Hurricane Katrina killed hundreds of people as it made landfall on New Orleans in 2005 - many of these deaths could have been avoided if alerts had been given one day earlier. Accurate weather forecasts are really life-saving.
🔥 Now, NASA and IBM just dropped a game-changing new model: the first ever foundation model for weather! This means, it's the first time we have a generalist model not restricted to one task, but able to predict 160 weather variables!
Prithvi WxC (Prithvi, “पृथ्वी”, is the Sanskrit name for Earth) - is a 2.3 billion parameter model, with an architecture close to previous vision transformers like Hiera.
💡 But it comes with some important tweaks: under the hood, Prithvi WxC uses a clever transformer-based architecture with 25 encoder and 5 decoder blocks. It alternates between "local" and "global" attention to capture both regional and global weather patterns.
𝗞𝗲𝘆 𝗶𝗻𝘀𝗶𝗴𝗵𝘁𝘀:
🔮 Nails short-term forecasts - Prithvi WxC crushed it on 6-12 hour predictions, even outperforming some traditional numerical weather models
🌀 Tracks hurricanes like a champ - For Hurricane Ida, it predicted the landfall location within 5 km (vs 20+ km errors from other AI models), which is a huge progress!
🔍 6x downscaling power - Can zoom in on weather data to 6x higher resolution with 4x lower error than basic methods
🌊 Models elusive gravity waves - Accurately simulates these crucial but hard-to-capture atmospheric oscillations
As climate change intensifies, tools like Prithvi WxC will become more and more crucial to avoid disasters!
Announcement post 👉 https://newsroom.ibm.com/2024-09-23-ibm-and-nasa-release-open-source-ai-model-on-hugging-face-for-weather-and-climate-applications
Model on the Hub 👉 https://huggingface.co/Prithvi-WxC
Thank you @clem for highlighting it!
Collections
12
-
Lost in the Middle: How Language Models Use Long Contexts
Paper • 2307.03172 • Published • 35 -
Efficient Estimation of Word Representations in Vector Space
Paper • 1301.3781 • Published • 6 -
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Paper • 1810.04805 • Published • 14 -
Attention Is All You Need
Paper • 1706.03762 • Published • 41
-
Judging LLM-as-a-judge with MT-Bench and Chatbot Arena
Paper • 2306.05685 • Published • 28 -
ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent
Paper • 2312.10003 • Published • 34 -
Leveraging Large Language Models for NLG Evaluation: A Survey
Paper • 2401.07103 • Published • 4 -
Prometheus: Inducing Fine-grained Evaluation Capability in Language Models
Paper • 2310.08491 • Published • 53
spaces
17
pinned
Running
64
🗺️🏕️
AI Travel Planner
Plan your next vacation with the help of an AI!
pinned
Running
180
🍫👀
Chunk Visualizer
Pick a text splitter => visualize chunks. Great for RAG.
pinned
Running
on
Zero
109
✍👀
Beam Search Visualizer
View how beam search decoding works, in detail!
Running
on
L4
🔎👀
Attention Visualizer
Discover how attention works in LLMs!
Runtime error
🚀
Retriever Tool
Running
👀
Text To Image
datasets
15
m-ric/newsletter
Updated
•
3
m-ric/songs_july_24
Viewer
•
Updated
•
85.6k
•
2
m-ric/huggingface_doc_qa_eval
Viewer
•
Updated
•
65
•
261
•
5
m-ric/agents_medium_benchmark
Viewer
•
Updated
•
172
•
6
•
2
m-ric/songs
Preview
•
Updated
•
4
m-ric/rag_scores_cookbook
Viewer
•
Updated
•
5
•
23
m-ric/images
Viewer
•
Updated
•
1
•
4
m-ric/agents_small_benchmark
Viewer
•
Updated
•
100
•
61
•
7
m-ric/huggingface_doc
Viewer
•
Updated
•
2.65k
•
1.19k
•
9
m-ric/transformers_documentation_en
Viewer
•
Updated
•
359
•
4