Inference for PROs
•
52
Victor Mustar PRO
victor
AI & ML interests
Building the UX of this website
Recent Activity
liked
a model
about 9 hours ago
answerdotai/ModernBERT-base
upvoted
a
paper
about 9 hours ago
Parallelized Autoregressive Visual Generation
Articles
Organizations
victor's activity
reacted to
Kseniase's
post with 👍
about 23 hours ago
Post
1416
**15 Agentic Systems and Frameworks of 2024**
This year, we started our “AI Agents and Agentic Workflows” series (https://www.turingpost.com/t/AI-Agents) to explore everything about AI agents step by step: all the vocabulary, how they work, and how to build them.
The huge interest in this series and the large number of studies conducted on agents showed that it was one of the most popular and important themes of the year. In 2025, most likely, agents will reach new highs – we will be covering that for you. Now, let’s review the agentic systems that have emerged this year.
Here is a list of 15 agentic systems and frameworks of 2024:
1. GUI Agents: A Survey (2412.13501)
2. Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level (2411.03562)
3. The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery (2408.06292)
4. MALT: Improving Reasoning with Multi-Agent LLM Training (2412.01928)
5. Agent S: An Open Agentic Framework that Uses Computers Like a Human (2410.08164)
6. Automated Design of Agentic Systems (2408.08435)
7. AgentInstruct: Toward Generative Teaching with Agentic Flows (2407.03502)
8. AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant (2410.18603)
9. WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents (2410.07484)
10. Generative Agent Simulations of 1,000 People (2411.10109)
11. DynaSaur: Large Language Agents Beyond Predefined Actions (2411.01747)
12. PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking (2410.12375)
13. Generative World Explorer (2411.11844)
14. Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines (2412.14684)
15. AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions (2410.20424)
Thanks for reading Turing Post!
Subscribe to receive new posts straight into your inbox -> https://www.turingpost.com/subscribe
This year, we started our “AI Agents and Agentic Workflows” series (https://www.turingpost.com/t/AI-Agents) to explore everything about AI agents step by step: all the vocabulary, how they work, and how to build them.
The huge interest in this series and the large number of studies conducted on agents showed that it was one of the most popular and important themes of the year. In 2025, most likely, agents will reach new highs – we will be covering that for you. Now, let’s review the agentic systems that have emerged this year.
Here is a list of 15 agentic systems and frameworks of 2024:
1. GUI Agents: A Survey (2412.13501)
2. Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level (2411.03562)
3. The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery (2408.06292)
4. MALT: Improving Reasoning with Multi-Agent LLM Training (2412.01928)
5. Agent S: An Open Agentic Framework that Uses Computers Like a Human (2410.08164)
6. Automated Design of Agentic Systems (2408.08435)
7. AgentInstruct: Toward Generative Teaching with Agentic Flows (2407.03502)
8. AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant (2410.18603)
9. WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents (2410.07484)
10. Generative Agent Simulations of 1,000 People (2411.10109)
11. DynaSaur: Large Language Agents Beyond Predefined Actions (2411.01747)
12. PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking (2410.12375)
13. Generative World Explorer (2411.11844)
14. Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines (2412.14684)
15. AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions (2410.20424)
Thanks for reading Turing Post!
Subscribe to receive new posts straight into your inbox -> https://www.turingpost.com/subscribe
reacted to
nroggendorff's
post with 👀
1 day ago
Post
1238
Can we please do something about this? It makes everything I do so much harder, and because my local machine is so terrible, I am forced to test in production. This makes debugging so difficult.
nroggendorff/system-exit
cc @victor
nroggendorff/system-exit
cc @victor
- 1 reply
reacted to
anton-l's
post with 🔥
5 days ago
Post
1934
Introducing 📐𝐅𝐢𝐧𝐞𝐌𝐚𝐭𝐡: the best public math pre-training dataset with 50B+ tokens!
HuggingFaceTB/finemath
Math remains challenging for LLMs and by training on FineMath we see considerable gains over other math datasets, especially on GSM8K and MATH.
We build the dataset by:
🛠️ carefully extracting math data from Common Crawl;
🔎 iteratively filtering and recalling high quality math pages using a classifier trained on synthetic annotations to identify math reasoning and deduction.
We conducted a series of ablations comparing the performance of Llama-3.2-3B-Base after continued pre-training on FineMath and observe notable gains compared to the baseline model and other public math datasets.
We hope this helps advance the performance of LLMs on math and reasoning! 🚀
We’re also releasing all the ablation models as well as the evaluation code.
HuggingFaceTB/finemath-6763fb8f71b6439b653482c2
HuggingFaceTB/finemath
Math remains challenging for LLMs and by training on FineMath we see considerable gains over other math datasets, especially on GSM8K and MATH.
We build the dataset by:
🛠️ carefully extracting math data from Common Crawl;
🔎 iteratively filtering and recalling high quality math pages using a classifier trained on synthetic annotations to identify math reasoning and deduction.
We conducted a series of ablations comparing the performance of Llama-3.2-3B-Base after continued pre-training on FineMath and observe notable gains compared to the baseline model and other public math datasets.
We hope this helps advance the performance of LLMs on math and reasoning! 🚀
We’re also releasing all the ablation models as well as the evaluation code.
HuggingFaceTB/finemath-6763fb8f71b6439b653482c2
reacted to
m-ric's
post with 🔥
5 days ago
Post
1599
After 6 years, BERT, the workhorse of encoder models, finally gets a replacement: 𝗪𝗲𝗹𝗰𝗼𝗺𝗲 𝗠𝗼𝗱𝗲𝗿𝗻𝗕𝗘𝗥𝗧! 🤗
We talk a lot about ✨Generative AI✨, meaning "Decoder version of the Transformers architecture", but this is only one of the ways to build LLMs: encoder models, that turn a sentence in a vector, are maybe even more widely used in industry than generative models.
The workhorse for this category has been BERT since its release in 2018 (that's prehistory for LLMs).
It's not a fancy 100B parameters supermodel (just a few hundred millions), but it's an excellent workhorse, kind of a Honda Civic for LLMs.
Many applications use BERT-family models - the top models in this category cumulate millions of downloads on the Hub.
➡️ Now a collaboration between Answer.AI and LightOn just introduced BERT's replacement: ModernBERT.
𝗧𝗟;𝗗𝗥:
🏛️ Architecture changes:
⇒ First, standard modernizations:
- Rotary positional embeddings (RoPE)
- Replace GeLU with GeGLU,
- Use Flash Attention 2
✨ The team also introduced innovative techniques like alternating attention instead of full attention, and sequence packing to get rid of padding overhead.
🥇 As a result, the model tops the game of encoder models:
It beats previous standard DeBERTaV3 for 1/5th the memory footprint, and runs 4x faster!
Read the blog post 👉 https://huggingface.co./blog/modernbert
We talk a lot about ✨Generative AI✨, meaning "Decoder version of the Transformers architecture", but this is only one of the ways to build LLMs: encoder models, that turn a sentence in a vector, are maybe even more widely used in industry than generative models.
The workhorse for this category has been BERT since its release in 2018 (that's prehistory for LLMs).
It's not a fancy 100B parameters supermodel (just a few hundred millions), but it's an excellent workhorse, kind of a Honda Civic for LLMs.
Many applications use BERT-family models - the top models in this category cumulate millions of downloads on the Hub.
➡️ Now a collaboration between Answer.AI and LightOn just introduced BERT's replacement: ModernBERT.
𝗧𝗟;𝗗𝗥:
🏛️ Architecture changes:
⇒ First, standard modernizations:
- Rotary positional embeddings (RoPE)
- Replace GeLU with GeGLU,
- Use Flash Attention 2
✨ The team also introduced innovative techniques like alternating attention instead of full attention, and sequence packing to get rid of padding overhead.
🥇 As a result, the model tops the game of encoder models:
It beats previous standard DeBERTaV3 for 1/5th the memory footprint, and runs 4x faster!
Read the blog post 👉 https://huggingface.co./blog/modernbert
- 1 reply
reacted to
akhaliq's
post with 🔥
5 days ago
Post
2237
Google drops Gemini 2.0 Flash Thinking
a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more
now available in anychat, try it out: akhaliq/anychat
a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more
now available in anychat, try it out: akhaliq/anychat
reacted to
Lewdiculous's
post with ➕
5 days ago
Post
1612
Hello fellow LLMers, just a quick notice that some of my activity will be moved into the AetherArchitectural Commuity and split with
@Aetherarchio
.
[here] https://huggingface.co./AetherArchitectural
All activity should be visible in the left side of my profile.
[here] https://huggingface.co./AetherArchitectural
All activity should be visible in the left side of my profile.
- 1 reply
reacted to
KnutJaegersberg's
post with 👍
5 days ago
Post
1215
Intelligence Potentiation: An Evolutionary Perspective on AI Agent Designs
I found it useful to think of AI agent design as progressing up a ladder, through evolutionary selection.
https://huggingface.co./blog/KnutJaegersberg/intelligence-potentiation
I found it useful to think of AI agent design as progressing up a ladder, through evolutionary selection.
https://huggingface.co./blog/KnutJaegersberg/intelligence-potentiation
reacted to
FranckAbgrall's
post with 🔥
5 days ago
Post
1028
🆕 It should now be easier to identify discussions or pull requests where repository owners are participating on HF, let us know it that helps 💬🤗
- 1 reply
reacted to
csabakecskemeti's
post with 🚀
6 days ago
Post
1187
tiiuae Falcon3 10B Q8 playground:
DevQuasar/Mi50
Also find my tiiuae Falcon3 Quant collection here:
https://huggingface.co./collections/DevQuasar/tiiuae-falcon3-676236626f3c57d1a19c6c1d
Enjoy!
DevQuasar/Mi50
Also find my tiiuae Falcon3 Quant collection here:
https://huggingface.co./collections/DevQuasar/tiiuae-falcon3-676236626f3c57d1a19c6c1d
Enjoy!
Excellent! ping @ThomasSimonini who might be interested
reacted to
neph1's
post with 🔥
6 days ago
Post
1034
For those interested in game development I've released an experimental finetune of Qwen2.5-Coder for Unity.
neph1/Qwen2.5-Coder-7B-Instruct-Unity
It's using a mix of open source datasets + one specifically made for this (also OS) with multiple responses.
Also thinking about making a code completion model, or one to have more architectural discussions with.
neph1/Qwen2.5-Coder-7B-Instruct-Unity
It's using a mix of open source datasets + one specifically made for this (also OS) with multiple responses.
Also thinking about making a code completion model, or one to have more architectural discussions with.
-
- 1 reply
reacted to
merve's
post with 🔥
6 days ago
Post
2240
Aya by Cohere For AI can now see! 👀
C4AI community has built Maya 8B, a new open-source multilingual VLM built on SigLIP and Aya 8B 🌱 works on 8 languages! 🗣️
The authors extend Llava dataset using Aya's translation capabilities with 558k examples!
ry it here kkr5155/maya_demo
Dataset maya-multimodal/pretrain
Model maya-multimodal/maya 👏
kudos @nahidalam and team
C4AI community has built Maya 8B, a new open-source multilingual VLM built on SigLIP and Aya 8B 🌱 works on 8 languages! 🗣️
The authors extend Llava dataset using Aya's translation capabilities with 558k examples!
ry it here kkr5155/maya_demo
Dataset maya-multimodal/pretrain
Model maya-multimodal/maya 👏
kudos @nahidalam and team
- 1 reply
reacted to
nataliaElv's
post with ❤️
7 days ago
Post
1592
If you are still wondering how the FineWeb2 annotations are done, how to follow the guidelines or how Argilla works, this is your video!
I go through a few samples of the FineWeb2 dataset and classify them based on their educational content. Check it out!
https://www.youtube.com/watch?v=_-ORB4WAVGU
I go through a few samples of the FineWeb2 dataset and classify them based on their educational content. Check it out!
https://www.youtube.com/watch?v=_-ORB4WAVGU
reacted to
davidberenstein1957's
post with 🔥
7 days ago
Post
4095
Introducing the Synthetic Data Generator, a user-friendly application that takes a no-code approach to creating custom datasets with Large Language Models (LLMs). The best part: A simple step-by-step process, making dataset creation a non-technical breeze, allowing anyone to create datasets and models in minutes and without any code.
Blog: https://huggingface.co./blog/synthetic-data-generator
Space: argilla/synthetic-data-generator
Blog: https://huggingface.co./blog/synthetic-data-generator
Space: argilla/synthetic-data-generator
- 4 replies
reacted to
lewtun's
post with 🔥🔥
7 days ago
Post
6405
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!
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
replied to
their
post
7 days ago
Out of curiosity do you use this menu? accessible for those models: https://huggingface.co./models?library=gguf&sort=trending
reacted to
lorraine2's
post with 🚀
7 days ago
Post
1964
🦙New NVIDIA paper: LLaMA-Mesh 🦙
We enable large language models to generate and understand 3D meshes by representing them as text and fine-tuning. This unifies the 3D and text modalities in a single model and preserves language abilities, unlocking conversational 3D creation with mesh understanding.
🔎 Project Page: https://research.nvidia.com/labs/toronto-ai/LLaMA-Mesh/
🕹️ Interactive Demo: Zhengyi/LLaMA-Mesh (courtesy of HuggingFace and Gradio)
📖 Full Paper: https://arxiv.org/abs/2411.09595
👨💻Code: https://github.com/nv-tlabs/LLaMa-Mesh
💾 Model Checkpoint: Zhengyi/LLaMA-Mesh
🧩 Blender Addon: https://github.com/huggingface/meshgen (courtesy of Dylan Ebert)
🎥 5-min Overview Video: https://youtu.be/eZNazN-1lPo?si=-idQa5aaceVw0Bbj (courtesy of AI Papers Academy)
We enable large language models to generate and understand 3D meshes by representing them as text and fine-tuning. This unifies the 3D and text modalities in a single model and preserves language abilities, unlocking conversational 3D creation with mesh understanding.
🔎 Project Page: https://research.nvidia.com/labs/toronto-ai/LLaMA-Mesh/
🕹️ Interactive Demo: Zhengyi/LLaMA-Mesh (courtesy of HuggingFace and Gradio)
📖 Full Paper: https://arxiv.org/abs/2411.09595
👨💻Code: https://github.com/nv-tlabs/LLaMa-Mesh
💾 Model Checkpoint: Zhengyi/LLaMA-Mesh
🧩 Blender Addon: https://github.com/huggingface/meshgen (courtesy of Dylan Ebert)
🎥 5-min Overview Video: https://youtu.be/eZNazN-1lPo?si=-idQa5aaceVw0Bbj (courtesy of AI Papers Academy)
reacted to
wenhuach's
post with 👀
7 days ago
Post
1770
AutoRound has demonstrated strong results even at 2-bit precision for VLM models like QWEN2-VL-72B. Check it out here:
OPEA/Qwen2-VL-72B-Instruct-int2-sym-inc.
-
- 4 replies
reacted to
MohamedRashad's
post with 🔥
8 days ago
Post
2437
For those Game Developers out there who wants a tool to generate them 3d assets of different game items. I built something for you 😅
JeffreyXiang/TRELLIS-image-large +
Qwen/Qwen2.5-72B-Instruct +
Freepik/flux.1-lite-8B-alpha =
MohamedRashad/Game-Items-Generator
Happy building 🎉
JeffreyXiang/TRELLIS-image-large +
Qwen/Qwen2.5-72B-Instruct +
Freepik/flux.1-lite-8B-alpha =
MohamedRashad/Game-Items-Generator
Happy building 🎉
- 1 reply