agents-course/certificates
Viewer
โข
Updated
โข
13
โข
54.4k
โข
32
Hugging Face Agents Course
Enterprise
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
agents-course's activity
burtenshawย
updated
a
dataset
5 minutes ago
davidberenstein1957ย
posted
an
update
about 20 hours ago
Post
881
๐ฅ Text2SQL, explore and share any data analysis!
๐ค Hugging Face - Dataset Studio is an amazing new feature.
๐ Start yourself: fka/awesome-chatgpt-prompts
๐บ YouTube: https://youtu.be/5LUZq7MHolA?feature=shared
๐ค Hugging Face - Dataset Studio is an amazing new feature.
๐ Start yourself: fka/awesome-chatgpt-prompts
๐บ YouTube: https://youtu.be/5LUZq7MHolA?feature=shared
burtenshawย
posted
an
update
1 day ago
Post
2135
Iโm super excited to work with
@mlabonne
to build the first practical example in the reasoning course.
๐ https://huggingface.co/reasoning-course
Here's a quick walk through of the first drop of material that works toward the use case:
- a fundamental introduction to reinforcement learning. Answering questions like, โwhat is a reward?โ and โhow do we create an environment for a language model?โ
- Then it focuses on Deepseek R1 by walking through the paper and highlighting key aspects. This is an old school way to learn ML topics, but it always works.
- Next, it takes to you Transformers Reinforcement Learning and demonstrates potential reward functions you could use. This is cool because it uses Marimo notebooks to visualise the reward.
- Finally, Maxime walks us through a real training notebook that uses GRPO to reduce generation length. Iโm really into this because it works and Maxime took the time to validate it share assets and logging from his own runs for you to compare with.
Maximeโs work and notebooks have been a major part of the open source community over the last few years. I, like everyone, have learnt so much from them.
๐ https://huggingface.co/reasoning-course
Here's a quick walk through of the first drop of material that works toward the use case:
- a fundamental introduction to reinforcement learning. Answering questions like, โwhat is a reward?โ and โhow do we create an environment for a language model?โ
- Then it focuses on Deepseek R1 by walking through the paper and highlighting key aspects. This is an old school way to learn ML topics, but it always works.
- Next, it takes to you Transformers Reinforcement Learning and demonstrates potential reward functions you could use. This is cool because it uses Marimo notebooks to visualise the reward.
- Finally, Maxime walks us through a real training notebook that uses GRPO to reduce generation length. Iโm really into this because it works and Maxime took the time to validate it share assets and logging from his own runs for you to compare with.
Maximeโs work and notebooks have been a major part of the open source community over the last few years. I, like everyone, have learnt so much from them.
davidberenstein1957ย
posted
an
update
2 days ago
Post
3953
๐ฅ Epic Agent Framework Showdown! Available today!
๐ต In the blue corner, the versatile challenger with a proven track record of knowledge retrieval: LlamaIndex!
๐ In the red corner, the defender, weighing in with lightweight efficiency: Hugging Face smolagents!
๐ URL: https://huggingface.co/agents-course
We just published the LlamaIndex unit for the agents course, and it is set to offer a great contrast between the smolagents unit by looking at
- What makes llama-index stand-out
- How the LlamaHub is used for integrations
- Creating QueryEngine components
- Using agents and tools
- Agentic and multi-agent workflows
The team has been working flat-out on this for a few weeks. Supported by Logan Markewich and Laurie Voss over at LlamaIndex.
Who won? You decide!
๐ต In the blue corner, the versatile challenger with a proven track record of knowledge retrieval: LlamaIndex!
๐ In the red corner, the defender, weighing in with lightweight efficiency: Hugging Face smolagents!
๐ URL: https://huggingface.co/agents-course
We just published the LlamaIndex unit for the agents course, and it is set to offer a great contrast between the smolagents unit by looking at
- What makes llama-index stand-out
- How the LlamaHub is used for integrations
- Creating QueryEngine components
- Using agents and tools
- Agentic and multi-agent workflows
The team has been working flat-out on this for a few weeks. Supported by Logan Markewich and Laurie Voss over at LlamaIndex.
Who won? You decide!
davidberenstein1957ย
posted
an
update
3 days ago
Post
2866
๐ซธ New release to push vector search to the Hub with vicinity and work with any serialisable objects.
๐งโ๐ซ KNN, HNSW, USEARCH, ANNOY, PYNNDESCENT, FAISS, and VOYAGER.
๐ Example Repo: minishlab/my-vicinity-repo
๐งโ๐ซ KNN, HNSW, USEARCH, ANNOY, PYNNDESCENT, FAISS, and VOYAGER.
๐ Example Repo: minishlab/my-vicinity-repo
burtenshawย
posted
an
update
8 days ago
Post
5216
I made a real time voice agent with FastRTC, smolagents, and hugging face inference providers. Check it out in this space:
๐ burtenshaw/coworking_agent
๐ burtenshaw/coworking_agent
-
- 9 replies
burtenshawย
posted
an
update
9 days ago
Post
6030
Now the Hugging Face agent course is getting real! With frameworks like smolagents, LlamaIndex, and LangChain.
๐ Follow the org for updates https://huggingface.co/agents-course
This week we are releasing the first framework unit in the course and itโs on smolagents. This is what the unit covers:
- why should you use smolagents vs another library?
- how to build agents that use code
- build multiagents systems
- use vision language models for browser use
The team has been working flat out on this for a few weeks. Led by @sergiopaniego and supported by smolagents author @m-ric .
๐ Follow the org for updates https://huggingface.co/agents-course
This week we are releasing the first framework unit in the course and itโs on smolagents. This is what the unit covers:
- why should you use smolagents vs another library?
- how to build agents that use code
- build multiagents systems
- use vision language models for browser use
The team has been working flat out on this for a few weeks. Led by @sergiopaniego and supported by smolagents author @m-ric .
Post
4525
We now have a Deep Research for academia: SurveyX automatically writes academic surveys nearly indistinguishable from human-written ones ๐ฅ
Researchers from Beijing and Shanghai just published the first application of a deep research system to academia: their algorithm, given a question, can give you a survey of all papers on the subject.
To make a research survey, you generally follow two steps, preparation (collect and organize papers) and writing (outline creation, writing, polishing). Researchers followed the same two steps and automated them.
๐ฏ For the preparation part, a key part is find all the important references on the given subject.
Researchers first cast a wide net of all relevant papers. But then finding the really important ones is like distilling knowledge from a haystack of information. To solve this challenge, they built an โAttributeTreeโ object that structures key information from citations. Ablating these AttributeTrees significantly decreased structure and synthesis scores, so they were really useful!
๐ For the writing part, key was to get a synthesis that's both short and true. This is not easy to get with LLMs! So they used methods like LLM-based deduplication to shorten the too verbose listings made by LLMs, and RAG to grab original quotes instead of made-up ones.
As a result, their system outperforms previous approaches by far!
As assessed by LLM-judges, the quality score os SurveyX even approaches this of human experts, with 4.59/5 vs 4.75/5 ๐
I advise you to read the paper, it's a great overview of the kind of assistants that we'll get in the short future! ๐ SurveyX: Academic Survey Automation via Large Language Models (2502.14776)
Their website shows examples of generated surveys ๐ http://www.surveyx.cn/
Researchers from Beijing and Shanghai just published the first application of a deep research system to academia: their algorithm, given a question, can give you a survey of all papers on the subject.
To make a research survey, you generally follow two steps, preparation (collect and organize papers) and writing (outline creation, writing, polishing). Researchers followed the same two steps and automated them.
๐ฏ For the preparation part, a key part is find all the important references on the given subject.
Researchers first cast a wide net of all relevant papers. But then finding the really important ones is like distilling knowledge from a haystack of information. To solve this challenge, they built an โAttributeTreeโ object that structures key information from citations. Ablating these AttributeTrees significantly decreased structure and synthesis scores, so they were really useful!
๐ For the writing part, key was to get a synthesis that's both short and true. This is not easy to get with LLMs! So they used methods like LLM-based deduplication to shorten the too verbose listings made by LLMs, and RAG to grab original quotes instead of made-up ones.
As a result, their system outperforms previous approaches by far!
As assessed by LLM-judges, the quality score os SurveyX even approaches this of human experts, with 4.59/5 vs 4.75/5 ๐
I advise you to read the paper, it's a great overview of the kind of assistants that we'll get in the short future! ๐ SurveyX: Academic Survey Automation via Large Language Models (2502.14776)
Their website shows examples of generated surveys ๐ http://www.surveyx.cn/
burtenshawย
posted
an
update
16 days ago
Post
7162
AGENTS + FINETUNING! This week Hugging Face learn has a whole pathway on finetuning for agentic applications. You can follow these two courses to get knowledge on levelling up your agent game beyond prompts:
1๏ธโฃ New Supervised Fine-tuning unit in the NLP Course https://huggingface.co/learn/nlp-course/en/chapter11/1
2๏ธโฃNew Finetuning for agents bonus module in the Agents Course https://huggingface.co/learn/agents-course/bonus-unit1/introduction
Fine-tuning will squeeze everything out of your model for how youโre using it, more than any prompt.
1๏ธโฃ New Supervised Fine-tuning unit in the NLP Course https://huggingface.co/learn/nlp-course/en/chapter11/1
2๏ธโฃNew Finetuning for agents bonus module in the Agents Course https://huggingface.co/learn/agents-course/bonus-unit1/introduction
Fine-tuning will squeeze everything out of your model for how youโre using it, more than any prompt.
-
- 2 replies
Post
2974
Less is More for Reasoning (LIMO): a 32B model fine-tuned with 817 examples can beat o1-preview on math reasoning! ๐คฏ
Do we really need o1's huge RL procedure to see reasoning emerge? It seems not.
Researchers from Shanghai Jiaotong University just demonstrated that carefully selected examples can boost math performance in large language models using SFT โno huge datasets or RL procedures needed.
Their procedure allows Qwen2.5-32B-Instruct to jump from 6.5% to 57% on AIME and from 59% to 95% on MATH, while using only 1% of the data in previous approaches.
โก The Less-is-More Reasoning Hypothesis:
โฃ Minimal but precise examples that showcase optimal reasoning patterns matter more than sheer quantity
โฃ Pre-training knowledge plus sufficient computational resources at inference levels up math skills
โก๏ธ Core techniques:
โฃ High-quality reasoning chains with self-verification steps
โฃ 817 handpicked problems that encourage deeper reasoning
โฃ Enough inference-time computation to allow extended reasoning
๐ช Efficiency gains:
โฃ Only 817 examples instead of 100k+
โฃ 40.5% absolute improvement across 10 diverse benchmarks, outperforming models trained on 100x more data
This really challenges the notion that SFT leads to memorization rather than generalization! And opens up reasoning to GPU-poor researchers ๐
Read the full paper here ๐ย LIMO: Less is More for Reasoning (2502.03387)
Do we really need o1's huge RL procedure to see reasoning emerge? It seems not.
Researchers from Shanghai Jiaotong University just demonstrated that carefully selected examples can boost math performance in large language models using SFT โno huge datasets or RL procedures needed.
Their procedure allows Qwen2.5-32B-Instruct to jump from 6.5% to 57% on AIME and from 59% to 95% on MATH, while using only 1% of the data in previous approaches.
โก The Less-is-More Reasoning Hypothesis:
โฃ Minimal but precise examples that showcase optimal reasoning patterns matter more than sheer quantity
โฃ Pre-training knowledge plus sufficient computational resources at inference levels up math skills
โก๏ธ Core techniques:
โฃ High-quality reasoning chains with self-verification steps
โฃ 817 handpicked problems that encourage deeper reasoning
โฃ Enough inference-time computation to allow extended reasoning
๐ช Efficiency gains:
โฃ Only 817 examples instead of 100k+
โฃ 40.5% absolute improvement across 10 diverse benchmarks, outperforming models trained on 100x more data
This really challenges the notion that SFT leads to memorization rather than generalization! And opens up reasoning to GPU-poor researchers ๐
Read the full paper here ๐ย LIMO: Less is More for Reasoning (2502.03387)
burtenshawย
posted
an
update
17 days ago
Post
3447
NEW COURSE! Weโre cooking hard on Hugging Face courses, and itโs not just agents. The NLP course is getting the same treatment with a new chapter on Supervised Fine-Tuning!
๐ Follow to get more updates https://huggingface.co/nlp-course
The new SFT chapter will guide you through these topics:
1๏ธโฃ Chat Templates: Master the art of structuring AI conversations for consistent and helpful responses.
2๏ธโฃ Supervised Fine-Tuning (SFT): Learn the core techniques to adapt pre-trained models to your specific outputs.
3๏ธโฃ Low Rank Adaptation (LoRA): Discover efficient fine-tuning methods that save memory and resources.
4๏ธโฃ Evaluation: Measure your model's performance and ensure top-notch results.
This is the first update in a series, so follow along if youโre upskilling in AI.
๐ Follow to get more updates https://huggingface.co/nlp-course
The new SFT chapter will guide you through these topics:
1๏ธโฃ Chat Templates: Master the art of structuring AI conversations for consistent and helpful responses.
2๏ธโฃ Supervised Fine-Tuning (SFT): Learn the core techniques to adapt pre-trained models to your specific outputs.
3๏ธโฃ Low Rank Adaptation (LoRA): Discover efficient fine-tuning methods that save memory and resources.
4๏ธโฃ Evaluation: Measure your model's performance and ensure top-notch results.
This is the first update in a series, so follow along if youโre upskilling in AI.
- 2 replies
Post
2867
๐๐ฟ๐ฒ๐ฎ๐ ๐ณ๐ฒ๐ฎ๐๐๐ฟ๐ฒ ๐ฎ๐น๐ฒ๐ฟ๐: you can now share agents to the Hub! ๐ฅณ๐ฅณ
And any agent pushed to Hub get a cool Space interface to directly chat with it.
This was a real technical challenge: for instance, serializing tools to export them meant that you needed to get all the source code for a tool, verify that it was standalone (not relying on external variables), and gathering all the packages required to make it run.
Go try it out! ๐ https://github.com/huggingface/smolagents
And any agent pushed to Hub get a cool Space interface to directly chat with it.
This was a real technical challenge: for instance, serializing tools to export them meant that you needed to get all the source code for a tool, verify that it was standalone (not relying on external variables), and gathering all the packages required to make it run.
Go try it out! ๐ https://github.com/huggingface/smolagents
- 2 replies
burtenshawย
posted
an
update
21 days ago
Post
3540
Hey, Iโm Ben and I work at Hugging Face.
Right now, Iโm focusing on educational stuff and getting loads of new people to build open AI models using free and open source tools.
Iโve made a collection of some of the tools Iโm building and using for teaching. Stuff like quizzes, code challenges, and certificates.
burtenshaw/tools-for-learning-ai-6797453caae193052d3638e2
Right now, Iโm focusing on educational stuff and getting loads of new people to build open AI models using free and open source tools.
Iโve made a collection of some of the tools Iโm building and using for teaching. Stuff like quizzes, code challenges, and certificates.
burtenshaw/tools-for-learning-ai-6797453caae193052d3638e2
- 1 reply
Post
2489
For those who haven't come across it yet, here's a handy trick to discuss an entire GitHub repo with an LLM:
=> Just replace "github" with "gitingest" in the url, and you get the whole repo as a single string that you can then paste in your LLMs
=> Just replace "github" with "gitingest" in the url, and you get the whole repo as a single string that you can then paste in your LLMs
Post
4801
"๐ฎ๐ฌ๐ฎ๐ฑ ๐๐ถ๐น๐น ๐ฏ๐ฒ ๐๐ต๐ฒ ๐๐ฒ๐ฎ๐ฟ ๐ผ๐ณ ๐๐ ๐ฎ๐ด๐ฒ๐ป๐๐": this statement has often been made, here are numbers to support it.
I've plotted the progress of AI agents on GAIA test set, and it seems they're headed to catch up with the human baseline in early 2026.
And that progress is still driven mostly by the improvement of base LLMs: progress would be even faster with fine-tuned agentic models.
I've plotted the progress of AI agents on GAIA test set, and it seems they're headed to catch up with the human baseline in early 2026.
And that progress is still driven mostly by the improvement of base LLMs: progress would be even faster with fine-tuned agentic models.
davidberenstein1957ย
posted
an
update
23 days ago
Post
3273
๐ Find banger tools for your smolagents!
I created the Tools gallery, which makes tools specifically developed by/for smolagents searchable and visible. This will help with:
- inspiration
- best practices
- finding cool tools
Space: davidberenstein1957/smolagents-and-tools
I created the Tools gallery, which makes tools specifically developed by/for smolagents searchable and visible. This will help with:
- inspiration
- best practices
- finding cool tools
Space: davidberenstein1957/smolagents-and-tools
- 1 reply
burtenshawย
posted
an
update
24 days ago
Post
9087
The Hugging Face agents course is finally out!
๐ https://huggingface.co/agents-course
This first unit of the course sets you up with all the fundamentals to become a pro in agents.
- What's an AI Agent?
- What are LLMs?
- Messages and Special Tokens
- Understanding AI Agents through the Thought-Action-Observation Cycle
- Thought, Internal Reasoning and the Re-Act Approach
- Actions, Enabling the Agent to Engage with Its Environment
- Observe, Integrating Feedback to Reflect and Adapt
๐ https://huggingface.co/agents-course
This first unit of the course sets you up with all the fundamentals to become a pro in agents.
- What's an AI Agent?
- What are LLMs?
- Messages and Special Tokens
- Understanding AI Agents through the Thought-Action-Observation Cycle
- Thought, Internal Reasoning and the Re-Act Approach
- Actions, Enabling the Agent to Engage with Its Environment
- Observe, Integrating Feedback to Reflect and Adapt
davidberenstein1957ย
posted
an
update
24 days ago
Post
2460
Fine-tune Deepseek-R1 with a Synthetic Reasoning Dataset
Blog: https://huggingface.co/blog/sdiazlor/fine-tune-deepseek-with-a-synthetic-reasoning-data
Blog: https://huggingface.co/blog/sdiazlor/fine-tune-deepseek-with-a-synthetic-reasoning-data
Post
3719
๐๐ฑ๐๐ฒ๐ป'๐ ๐ป๐ฒ๐ ๐๐ฎ๐๐ฎ ๐๐ด๐ฒ๐ป๐๐ ๐๐ฒ๐ป๐ฐ๐ต๐บ๐ฎ๐ฟ๐ธ ๐๐ต๐ผ๐๐ ๐๐ต๐ฎ๐ ๐๐ฒ๐ฒ๐ฝ๐ฆ๐ฒ๐ฒ๐ธ-๐ฅ๐ญ ๐๐๐ฟ๐๐ด๐ด๐น๐ฒ๐ ๐ผ๐ป ๐ฑ๐ฎ๐๐ฎ ๐๐ฐ๐ถ๐ฒ๐ป๐ฐ๐ฒ ๐๐ฎ๐๐ธ๐! โ
โก๏ธ How well do reasoning models perform on agentic tasks? Until now, all indicators seemed to show that they worked really well. On our recent reproduction of Deep Search, OpenAI's o1 was by far the best model to power an agentic system.
So when our partner Adyen built a huge benchmark of 450 data science tasks, and built data agents with smolagents to test different models, I expected reasoning models like o1 or DeepSeek-R1 to destroy the tasks at hand.
๐ But they really missed the mark. DeepSeek-R1 only got 1 or 2 out of 10 questions correct. Similarly, o1 was only at ~13% correct answers.
๐ง These results really surprised us. We thoroughly checked them, we even thought our APIs for DeepSeek were broken and colleagues Leandro Anton helped me start custom instances of R1 on our own H100s to make sure it worked well.
But there seemed to be no mistake. Reasoning LLMs actually did not seem that smart. Often, these models made basic mistakes, like forgetting the content of a folder that they had just explored, misspelling file names, or hallucinating data. Even though they do great at exploring webpages through several steps, the same level of multi-step planning seemed much harder to achieve when reasoning over files and data.
It seems like there's still lots of work to do in the Agents x Data space. Congrats to Adyen for this great benchmark, looking forward to see people proposing better agents! ๐
Read more in the blog post ๐ https://huggingface.co/blog/dabstep
โก๏ธ How well do reasoning models perform on agentic tasks? Until now, all indicators seemed to show that they worked really well. On our recent reproduction of Deep Search, OpenAI's o1 was by far the best model to power an agentic system.
So when our partner Adyen built a huge benchmark of 450 data science tasks, and built data agents with smolagents to test different models, I expected reasoning models like o1 or DeepSeek-R1 to destroy the tasks at hand.
๐ But they really missed the mark. DeepSeek-R1 only got 1 or 2 out of 10 questions correct. Similarly, o1 was only at ~13% correct answers.
๐ง These results really surprised us. We thoroughly checked them, we even thought our APIs for DeepSeek were broken and colleagues Leandro Anton helped me start custom instances of R1 on our own H100s to make sure it worked well.
But there seemed to be no mistake. Reasoning LLMs actually did not seem that smart. Often, these models made basic mistakes, like forgetting the content of a folder that they had just explored, misspelling file names, or hallucinating data. Even though they do great at exploring webpages through several steps, the same level of multi-step planning seemed much harder to achieve when reasoning over files and data.
It seems like there's still lots of work to do in the Agents x Data space. Congrats to Adyen for this great benchmark, looking forward to see people proposing better agents! ๐
Read more in the blog post ๐ https://huggingface.co/blog/dabstep
burtenshawย
posted
an
update
28 days ago
Post
3665
SmolLM2 paper is out! ๐
๐ Why do I love it? Because it facilitates teaching and learning!
Over the past few months I've engaged with (no joke) thousands of students based on SmolLM.
- People have inferred, fine-tuned, aligned, and evaluated this smol model.
- People used they're own machines and they've used free tools like colab, kaggle, and spaces.
- People tackled use cases in their job, for fun, in their own language, and with their friends.
upvote the paper SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model (2502.02737)
๐ Why do I love it? Because it facilitates teaching and learning!
Over the past few months I've engaged with (no joke) thousands of students based on SmolLM.
- People have inferred, fine-tuned, aligned, and evaluated this smol model.
- People used they're own machines and they've used free tools like colab, kaggle, and spaces.
- People tackled use cases in their job, for fun, in their own language, and with their friends.
upvote the paper SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model (2502.02737)
- 1 reply