Local AI with Docker's Testcontainers
•
7
Joseph [open/acc] Pollack
Tonic
AI & ML interests
🤖Making robots to help people learn things quicker 👩🏻🚀🚀
Recent Activity
liked
a Space
about 7 hours ago
cosimotaiuti/team9
updated
a Space
about 10 hours ago
The-Last-Message/demo-25-01-1515
published
a Space
about 11 hours ago
The-Last-Message/demo-25-01-1515
Articles
Organizations
Tonic's activity
loving the new recap format a lot 🏆
reacted to
merve's
post with 🧠
about 17 hours ago
Post
1713
Oof, what a week! 🥵 So many things have happened, let's recap!
merve/jan-24-releases-6793d610774073328eac67a9
Multimodal 💬
- We have released SmolVLM -- tiniest VLMs that come in 256M and 500M, with it's retrieval models ColSmol for multimodal RAG 💗
- UI-TARS are new models by ByteDance to unlock agentic GUI control 🤯 in 2B, 7B and 72B
- Alibaba DAMO lab released VideoLlama3, new video LMs that come in 2B and 7B
- MiniMaxAI released Minimax-VL-01, where decoder is based on MiniMax-Text-01 456B MoE model with long context
- Dataset: Yale released a new benchmark called MMVU
- Dataset: CAIS released Humanity's Last Exam (HLE) a new challenging MM benchmark
LLMs 📖
- DeepSeek-R1 & DeepSeek-R1-Zero: gigantic 660B reasoning models by DeepSeek, and six distilled dense models, on par with o1 with MIT license! 🤯
- Qwen2.5-Math-PRM: new math models by Qwen in 7B and 72B
- NVIDIA released AceMath and AceInstruct, new family of models and their datasets (SFT and reward ones too!)
Audio 🗣️
- Llasa is a new speech synthesis model based on Llama that comes in 1B,3B, and 8B
- TangoFlux is a new audio generation model trained from scratch and aligned with CRPO
Image/Video/3D Generation ⏯️
- Flex.1-alpha is a new 8B pre-trained diffusion model by ostris similar to Flux
- tencent released Hunyuan3D-2, new 3D asset generation from images
Multimodal 💬
- We have released SmolVLM -- tiniest VLMs that come in 256M and 500M, with it's retrieval models ColSmol for multimodal RAG 💗
- UI-TARS are new models by ByteDance to unlock agentic GUI control 🤯 in 2B, 7B and 72B
- Alibaba DAMO lab released VideoLlama3, new video LMs that come in 2B and 7B
- MiniMaxAI released Minimax-VL-01, where decoder is based on MiniMax-Text-01 456B MoE model with long context
- Dataset: Yale released a new benchmark called MMVU
- Dataset: CAIS released Humanity's Last Exam (HLE) a new challenging MM benchmark
LLMs 📖
- DeepSeek-R1 & DeepSeek-R1-Zero: gigantic 660B reasoning models by DeepSeek, and six distilled dense models, on par with o1 with MIT license! 🤯
- Qwen2.5-Math-PRM: new math models by Qwen in 7B and 72B
- NVIDIA released AceMath and AceInstruct, new family of models and their datasets (SFT and reward ones too!)
Audio 🗣️
- Llasa is a new speech synthesis model based on Llama that comes in 1B,3B, and 8B
- TangoFlux is a new audio generation model trained from scratch and aligned with CRPO
Image/Video/3D Generation ⏯️
- Flex.1-alpha is a new 8B pre-trained diffusion model by ostris similar to Flux
- tencent released Hunyuan3D-2, new 3D asset generation from images
- 6 replies
reacted to
KnutJaegersberg's
post with 🚀
about 17 hours ago
Post
559
Artificial Kuramoto Oscillatory Neurons
Artificial Kuramoto Oscillatory Neurons (AKOrN) differ from traditional artificial neurons by oscillating, rather than just turning on or off. Each neuron is represented by a rotating vector on a sphere, influenced by its connections to other neurons. This behavior is based on the Kuramoto model, which describes how oscillators (like neurons) tend to synchronize, similar to pendulums swinging in unison.
Key points:
Oscillating Neurons: Each AKOrN’s rotation is influenced by its connections, and they try to synchronize or oppose each other.
Synchronization: When neurons synchronize, they "bind," allowing the network to represent complex concepts (e.g., "a blue square toy") by compressing information.
Updating Mechanism: Neurons update their rotations based on connected neurons, input stimuli, and their natural frequency, using a Kuramoto update formula.
Network Structure: AKOrNs can be used in various network layers, with iterative blocks combining Kuramoto layers and feature extraction modules.
Reasoning: This model can perform reasoning tasks, like solving Sudoku puzzles, by adjusting neuron interactions.
Advantages: AKOrNs offer robust feature binding, reasoning capabilities, resistance to adversarial data, and well-calibrated uncertainty estimation.
In summary, AKOrN's oscillatory neurons and synchronization mechanisms enable the network to learn, reason, and handle complex tasks like image classification and object discovery with enhanced robustness and flexibility.
yt
https://www.youtube.com/watch?v=i3fRf6fb9ZM
paper
https://arxiv.org/html/2410.13821v1
Artificial Kuramoto Oscillatory Neurons (AKOrN) differ from traditional artificial neurons by oscillating, rather than just turning on or off. Each neuron is represented by a rotating vector on a sphere, influenced by its connections to other neurons. This behavior is based on the Kuramoto model, which describes how oscillators (like neurons) tend to synchronize, similar to pendulums swinging in unison.
Key points:
Oscillating Neurons: Each AKOrN’s rotation is influenced by its connections, and they try to synchronize or oppose each other.
Synchronization: When neurons synchronize, they "bind," allowing the network to represent complex concepts (e.g., "a blue square toy") by compressing information.
Updating Mechanism: Neurons update their rotations based on connected neurons, input stimuli, and their natural frequency, using a Kuramoto update formula.
Network Structure: AKOrNs can be used in various network layers, with iterative blocks combining Kuramoto layers and feature extraction modules.
Reasoning: This model can perform reasoning tasks, like solving Sudoku puzzles, by adjusting neuron interactions.
Advantages: AKOrNs offer robust feature binding, reasoning capabilities, resistance to adversarial data, and well-calibrated uncertainty estimation.
In summary, AKOrN's oscillatory neurons and synchronization mechanisms enable the network to learn, reason, and handle complex tasks like image classification and object discovery with enhanced robustness and flexibility.
yt
https://www.youtube.com/watch?v=i3fRf6fb9ZM
paper
https://arxiv.org/html/2410.13821v1
-
- 2 replies
replied to
KnutJaegersberg's
post
about 17 hours ago
🐿️
reacted to
chansung's
post with 👍
3 days ago
Post
1878
Simple summarization of Evolving Deeper LLM Thinking (Google DeepMind)
The process starts by posing a question.
1) The LLM generates initial responses.
2) These generated responses are evaluated according to specific criteria (program-based checker).
3) The LLM critiques the evaluated results.
4) The LLM refines the responses based on the evaluation, critique, and original responses.
The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged).
Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios.
However, there are two major drawbacks:
🤔 An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
🤔 The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.)
https://arxiv.org/abs/2501.09891
The process starts by posing a question.
1) The LLM generates initial responses.
2) These generated responses are evaluated according to specific criteria (program-based checker).
3) The LLM critiques the evaluated results.
4) The LLM refines the responses based on the evaluation, critique, and original responses.
The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged).
Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios.
However, there are two major drawbacks:
🤔 An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
🤔 The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.)
https://arxiv.org/abs/2501.09891
reacted to
rwightman's
post with 👍
7 days ago
Post
1235
I re-worked the JuptyerLab Space template recently. It's optimized for
timm use, but will work great with transformers and other libs. Updated the base image, Python 3.12, Pillow-SIMD before better CPU use with image preprocessing, and made a number of other tweaks. From the Jupyter launcher you can run the terminal and setup a timm environment in moments with setup_timm_dev or setup_timm_scripts helpers. Give it a try,
timm/jupyterlab-timm
reacted to
prithivMLmods's
post with 😎
9 days ago
Post
2548
ChemQwen-vL [ Qwen for Chem Vision ] 🧑🏻🔬
🧪Model : prithivMLmods/ChemQwen-vL
📝ChemQwen-vL is a vision-language model fine-tuned based on the Qwen2VL-2B Instruct model. It has been trained using the International Chemical Identifier (InChI) format for chemical compounds and is optimized for chemical compound identification. The model excels at generating the InChI and providing descriptions of chemical compounds based on their images. Its architecture operates within a multi-modal framework, combining image-text-text capabilities. It has been fine-tuned using datasets from: https://iupac.org/projects/
📒Colab Demo: https://tinyurl.com/2pn8x6u7, Collection : https://tinyurl.com/2mt5bjju
Inference with the documentation is possible with the help of the ReportLab library. https://pypi.org/project/reportlab/
🤗: @prithivMLmods
🧪Model : prithivMLmods/ChemQwen-vL
📝ChemQwen-vL is a vision-language model fine-tuned based on the Qwen2VL-2B Instruct model. It has been trained using the International Chemical Identifier (InChI) format for chemical compounds and is optimized for chemical compound identification. The model excels at generating the InChI and providing descriptions of chemical compounds based on their images. Its architecture operates within a multi-modal framework, combining image-text-text capabilities. It has been fine-tuned using datasets from: https://iupac.org/projects/
📒Colab Demo: https://tinyurl.com/2pn8x6u7, Collection : https://tinyurl.com/2mt5bjju
Inference with the documentation is possible with the help of the ReportLab library. https://pypi.org/project/reportlab/
🤗: @prithivMLmods
- 1 reply
posted
an
update
10 days ago
Post
1433
🙋🏻♂️ Hey there folks ,
Facebook AI just released JASCO models that make music stems .
you can try it out here : Tonic/audiocraft
hope you like it
Facebook AI just released JASCO models that make music stems .
you can try it out here : Tonic/audiocraft
hope you like it
reacted to
tomaarsen's
post with 🔥🔥❤️
10 days ago
Post
4318
🏎️ Today I'm introducing a method to train static embedding models that run 100x to 400x faster on CPU than common embedding models, while retaining 85%+ of the quality! Including 2 fully open models: training scripts, datasets, metrics.
We apply our recipe to train 2 Static Embedding models that we release today! We release:
2️⃣ an English Retrieval model and a general-purpose Multilingual similarity model (e.g. classification, clustering, etc.), both Apache 2.0
🧠 my modern training strategy: ideation -> dataset choice -> implementation -> evaluation
📜 my training scripts, using the Sentence Transformers library
📊 my Weights & Biases reports with losses & metrics
📕 my list of 30 training and 13 evaluation datasets
The 2 Static Embedding models have the following properties:
🏎️ Extremely fast, e.g. 107500 sentences per second on a consumer CPU, compared to 270 for 'all-mpnet-base-v2' and 56 for 'gte-large-en-v1.5'
0️⃣ Zero active parameters: No Transformer blocks, no attention, not even a matrix multiplication. Super speed!
📏 No maximum sequence length! Embed texts at any length (note: longer texts may embed worse)
📐 Linear instead of exponential complexity: 2x longer text takes 2x longer, instead of 2.5x or more.
🪆 Matryoshka support: allow you to truncate embeddings with minimal performance loss (e.g. 4x smaller with a 0.56% perf. decrease for English Similarity tasks)
Check out the full blogpost if you'd like to 1) use these lightning-fast models or 2) learn how to train them with consumer-level hardware: https://huggingface.co/blog/static-embeddings
The blogpost contains a lengthy list of possible advancements; I'm very confident that our 2 models are only the tip of the iceberg, and we may be able to get even better performance.
Alternatively, check out the models:
* sentence-transformers/static-retrieval-mrl-en-v1
* sentence-transformers/static-similarity-mrl-multilingual-v1
We apply our recipe to train 2 Static Embedding models that we release today! We release:
2️⃣ an English Retrieval model and a general-purpose Multilingual similarity model (e.g. classification, clustering, etc.), both Apache 2.0
🧠 my modern training strategy: ideation -> dataset choice -> implementation -> evaluation
📜 my training scripts, using the Sentence Transformers library
📊 my Weights & Biases reports with losses & metrics
📕 my list of 30 training and 13 evaluation datasets
The 2 Static Embedding models have the following properties:
🏎️ Extremely fast, e.g. 107500 sentences per second on a consumer CPU, compared to 270 for 'all-mpnet-base-v2' and 56 for 'gte-large-en-v1.5'
0️⃣ Zero active parameters: No Transformer blocks, no attention, not even a matrix multiplication. Super speed!
📏 No maximum sequence length! Embed texts at any length (note: longer texts may embed worse)
📐 Linear instead of exponential complexity: 2x longer text takes 2x longer, instead of 2.5x or more.
🪆 Matryoshka support: allow you to truncate embeddings with minimal performance loss (e.g. 4x smaller with a 0.56% perf. decrease for English Similarity tasks)
Check out the full blogpost if you'd like to 1) use these lightning-fast models or 2) learn how to train them with consumer-level hardware: https://huggingface.co/blog/static-embeddings
The blogpost contains a lengthy list of possible advancements; I'm very confident that our 2 models are only the tip of the iceberg, and we may be able to get even better performance.
Alternatively, check out the models:
* sentence-transformers/static-retrieval-mrl-en-v1
* sentence-transformers/static-similarity-mrl-multilingual-v1
- 1 reply
reacted to
burtenshaw's
post with 👍🧠🧠
10 days ago
Post
37513
We’re launching a FREE and CERTIFIED course on Agents!
We're thrilled to announce the launch of the Hugging Face Agents course on Learn! This interactive, certified course will guide you through building and deploying your own AI agents.
Here's what you'll learn:
- Understanding Agents: We'll break down the fundamentals of AI agents, showing you how they use LLMs to perceive their environment (observations), reason about it (thoughts), and take actions. Think of a smart assistant that can book appointments, answer emails, or even write code based on your instructions.
- Building with Frameworks: You'll dive into popular agent frameworks like LangChain, LlamaIndex and smolagents. These tools provide the building blocks for creating complex agent behaviors.
- Real-World Applications: See how agents are used in practice, from automating SQL queries to generating code and summarizing complex documents.
- Certification: Earn a certification by completing the course modules, implementing a use case, and passing a benchmark assessment. This proves your skills in building and deploying AI agents.
Audience
This course is designed for anyone interested in the future of AI. Whether you're a developer, data scientist, or simply curious about AI, this course will equip you with the knowledge and skills to build your own intelligent agents.
Enroll today and start building the next generation of AI agent applications!
https://bit.ly/hf-learn-agents
We're thrilled to announce the launch of the Hugging Face Agents course on Learn! This interactive, certified course will guide you through building and deploying your own AI agents.
Here's what you'll learn:
- Understanding Agents: We'll break down the fundamentals of AI agents, showing you how they use LLMs to perceive their environment (observations), reason about it (thoughts), and take actions. Think of a smart assistant that can book appointments, answer emails, or even write code based on your instructions.
- Building with Frameworks: You'll dive into popular agent frameworks like LangChain, LlamaIndex and smolagents. These tools provide the building blocks for creating complex agent behaviors.
- Real-World Applications: See how agents are used in practice, from automating SQL queries to generating code and summarizing complex documents.
- Certification: Earn a certification by completing the course modules, implementing a use case, and passing a benchmark assessment. This proves your skills in building and deploying AI agents.
Audience
This course is designed for anyone interested in the future of AI. Whether you're a developer, data scientist, or simply curious about AI, this course will equip you with the knowledge and skills to build your own intelligent agents.
Enroll today and start building the next generation of AI agent applications!
https://bit.ly/hf-learn-agents
- 22 replies
reacted to
lianghsun's
post with ❤️
10 days ago
Post
1681
🖖 Let me introduce the work I've done over the past three months: 𝗟𝗹𝗮𝗺𝗮-𝟯.𝟮-𝗧𝗮𝗶𝘄𝗮𝗻-𝟯𝗕 and 𝗟𝗹𝗮𝗺𝗮-𝟯.𝟮-𝗧𝗮𝗶𝘄𝗮𝗻-𝟯𝗕-𝗜𝗻𝘀𝘁𝗿𝘂𝗰𝘁, now open-sourced on 🤗 Hugging Face.
𝗹𝗶𝗮𝗻𝗴𝗵𝘀𝘂𝗻/𝗟𝗹𝗮𝗺𝗮-𝟯.𝟮-𝗧𝗮𝗶𝘄𝗮𝗻-𝟯𝗕: This model is built on top of 𝗺𝗲𝘁𝗮-𝗹𝗹𝗮𝗺𝗮/𝗟𝗹𝗮𝗺𝗮-𝟯.𝟮-𝟯𝗕 with continual pretraining. The training dataset consists of a mixture of Traditional Chinese and multilingual texts in specific proportions, including 20B tokens of Traditional Chinese text.
𝗹𝗶𝗮𝗻𝗴𝗵𝘀𝘂𝗻/𝗟𝗹𝗮𝗺𝗮-𝟯.𝟮-𝗧𝗮𝗶𝘄𝗮𝗻-𝟯𝗕-𝗜𝗻𝘀𝘁𝗿𝘂𝗰𝘁: This is a fine-tuned conversational model based on the foundation model.
This Llama-3.2-Taiwan open-source project is currently a one-person effort (yes, I did everything from text preparation — so exhausting!). If you're interested, feel free to join the Discord server for discussions.
🅱🅴🅽🅲🅷🅼🅰🆁🅺🅸🅽🅶
The evaluation was conducted using ikala/tmmluplus, though the README page does not yet reflect the latest results. The performance is close to the previous versions, indicating that further improvements might require adding more specialized knowledge in the datasets.
🅰 🅲🅰🅻🅻 🅵🅾🆁 🆂🆄🅿🅿🅾🆁🆃
If anyone is willing to provide compute resources, it would be greatly appreciated to help this project continue and grow. 💪
---
🏔️ Foundation model: lianghsun/Llama-3.2-Taiwan-3B
🤖 Instruction model: lianghsun/Llama-3.2-Taiwan-3B-Instruct
⚡ GGUF: lianghsun/Llama-3.2-Taiwan-3B-Instruct-GGUF
𝗹𝗶𝗮𝗻𝗴𝗵𝘀𝘂𝗻/𝗟𝗹𝗮𝗺𝗮-𝟯.𝟮-𝗧𝗮𝗶𝘄𝗮𝗻-𝟯𝗕: This model is built on top of 𝗺𝗲𝘁𝗮-𝗹𝗹𝗮𝗺𝗮/𝗟𝗹𝗮𝗺𝗮-𝟯.𝟮-𝟯𝗕 with continual pretraining. The training dataset consists of a mixture of Traditional Chinese and multilingual texts in specific proportions, including 20B tokens of Traditional Chinese text.
𝗹𝗶𝗮𝗻𝗴𝗵𝘀𝘂𝗻/𝗟𝗹𝗮𝗺𝗮-𝟯.𝟮-𝗧𝗮𝗶𝘄𝗮𝗻-𝟯𝗕-𝗜𝗻𝘀𝘁𝗿𝘂𝗰𝘁: This is a fine-tuned conversational model based on the foundation model.
This Llama-3.2-Taiwan open-source project is currently a one-person effort (yes, I did everything from text preparation — so exhausting!). If you're interested, feel free to join the Discord server for discussions.
🅱🅴🅽🅲🅷🅼🅰🆁🅺🅸🅽🅶
The evaluation was conducted using ikala/tmmluplus, though the README page does not yet reflect the latest results. The performance is close to the previous versions, indicating that further improvements might require adding more specialized knowledge in the datasets.
🅰 🅲🅰🅻🅻 🅵🅾🆁 🆂🆄🅿🅿🅾🆁🆃
If anyone is willing to provide compute resources, it would be greatly appreciated to help this project continue and grow. 💪
---
🏔️ Foundation model: lianghsun/Llama-3.2-Taiwan-3B
🤖 Instruction model: lianghsun/Llama-3.2-Taiwan-3B-Instruct
⚡ GGUF: lianghsun/Llama-3.2-Taiwan-3B-Instruct-GGUF
-
- 4 replies
these two organisations have an opinion , many people in the world have another . it might be surprising to you that they can be safely ignored and are not the arbiturs of truth , just as it might be amazing learn nobody needs people that dont put licences on their publications to give lessons on licences https://huggingface.co/datasets/JLouisBiz/my-distiset-be899639/tree/main so just enjoy the model or ignore it :-)
posted
an
update
12 days ago
Post
2357
🙋🏻♂️Hey there folks , Open LLM Europe just released Lucie 7B-Instruct model , a billingual instruct model trained on open data ! You can check out my unofficial demo here while we wait for the official inference api from the group :
Tonic/Lucie-7B hope you like it 🚀
reacted to
merve's
post with ❤️
13 days ago
Post
3839
there's a new multimodal retrieval model in town 🤠
LlamaIndex released vdr-2b-multi-v1
> uses 70% less image tokens, yet outperforming other dse-qwen2 based models
> 3x faster inference with less VRAM 💨
> shrinkable with matryoshka 🪆
> can do cross-lingual retrieval!
Collection: llamaindex/visual-document-retrieval-678151d19d2758f78ce910e1 (with models and datasets)
Demo: llamaindex/multimodal_vdr_demo
Learn more from their blog post here https://huggingface.co/blog/vdr-2b-multilingual 📖
LlamaIndex released vdr-2b-multi-v1
> uses 70% less image tokens, yet outperforming other dse-qwen2 based models
> 3x faster inference with less VRAM 💨
> shrinkable with matryoshka 🪆
> can do cross-lingual retrieval!
Collection: llamaindex/visual-document-retrieval-678151d19d2758f78ce910e1 (with models and datasets)
Demo: llamaindex/multimodal_vdr_demo
Learn more from their blog post here https://huggingface.co/blog/vdr-2b-multilingual 📖
reacted to
hexgrad's
post with 👀
16 days ago
Post
17956
📣 Looking for labeled, high-quality synthetic audio/TTS data 📣 Have you been or are you currently calling API endpoints from OpenAI, ElevenLabs, etc? Do you have labeled audio data sitting around gathering dust? Let's talk! Join https://discord.gg/QuGxSWBfQy or comment down below.
If your data exceeds quantity & quality thresholds and is approved into the next hexgrad/Kokoro-82M training mix, and you permissively DM me the data under an effective Apache license, then I will DM back the corresponding voicepacks for YOUR data if/when the next Apache-licensed Kokoro base model drops.
What does this mean? If you've been calling closed-source TTS or audio API endpoints to:
- Build voice agents
- Make long-form audio, like audiobooks or podcasts
- Handle customer support, etc
Then YOU can contribute to the training mix and get useful artifacts in return. ❤️
More details at hexgrad/Kokoro-82M#21
If your data exceeds quantity & quality thresholds and is approved into the next hexgrad/Kokoro-82M training mix, and you permissively DM me the data under an effective Apache license, then I will DM back the corresponding voicepacks for YOUR data if/when the next Apache-licensed Kokoro base model drops.
What does this mean? If you've been calling closed-source TTS or audio API endpoints to:
- Build voice agents
- Make long-form audio, like audiobooks or podcasts
- Handle customer support, etc
Then YOU can contribute to the training mix and get useful artifacts in return. ❤️
More details at hexgrad/Kokoro-82M#21
- 21 replies