my1
Collection
29 items
โข
Updated
wb
whitebill
AI & ML interests
None yet
Recent Activity
updated
a collection
about 11 hours ago
my1
updated
a collection
2 days ago
my1
Organizations
whitebill's activity
updated
a
collection
about 11 hours ago
updated
a
collection
2 days ago
reacted to
openfree's
post with ๐
24 days ago
Post
6075
๐ฅ Creating a qwen3-30b-a3b / qwen3-235b-a22b Chatbot with Deep Research Capabilities ๐
openfree/qwen3-30b-a3b-research
openfree/qwen3-235b-a22b-research
Hello AI researchers! ๐ Today I'm introducing a powerful chatbot implementation with real-time web search capabilities.
โจ Key Features
๐ง Chatbot based on qwen3-30b-a3b and llama4-maverick models
๐ LLM-based optimal keyword extraction
๐ Real-time web search using SerpHouse API
๐ฌ Streaming responses for natural conversation experience
๐ ๏ธ Technology Stack
Gradio: Implementation of intuitive web interface
Fireworks.ai API: Access to high-performance LLM models
SerpHouse API: Collection of real-time search results
๐ Application Areas
Question answering systems requiring up-to-date information
Providing current information beyond training data
Delivering reliable information with accurate sources
Add real-time search capabilities to your AI applications with this project! ๐ Leave your questions or suggestions in the comments! Let's improve it together~ ๐ช
#LLM #ArtificialIntelligence #WebSearch #Gradio #DeepResearch #OpenSource
openfree/qwen3-30b-a3b-research
openfree/qwen3-235b-a22b-research
Hello AI researchers! ๐ Today I'm introducing a powerful chatbot implementation with real-time web search capabilities.
โจ Key Features
๐ง Chatbot based on qwen3-30b-a3b and llama4-maverick models
๐ LLM-based optimal keyword extraction
๐ Real-time web search using SerpHouse API
๐ฌ Streaming responses for natural conversation experience
๐ ๏ธ Technology Stack
Gradio: Implementation of intuitive web interface
Fireworks.ai API: Access to high-performance LLM models
SerpHouse API: Collection of real-time search results
๐ Application Areas
Question answering systems requiring up-to-date information
Providing current information beyond training data
Delivering reliable information with accurate sources
Add real-time search capabilities to your AI applications with this project! ๐ Leave your questions or suggestions in the comments! Let's improve it together~ ๐ช
#LLM #ArtificialIntelligence #WebSearch #Gradio #DeepResearch #OpenSource
updated
a
collection
about 1 month ago
updated
a
collection
about 2 months ago
updated
a
collection
2 months ago
updated
a
collection
3 months ago
upvoted
a
collection
3 months ago
reacted to
Jaward's
post with ๐
4 months ago
Post
3663
ByteDance drops OmniHuman๐ฅ
This is peak SOTA performance - flawless natural gestures with perfect lip sync and facial expressions. This is the second time they've released SOTA level talking-heads only this time with hands and body motion.
Project: https://omnihuman-lab.github.io/
This is peak SOTA performance - flawless natural gestures with perfect lip sync and facial expressions. This is the second time they've released SOTA level talking-heads only this time with hands and body motion.
Project: https://omnihuman-lab.github.io/
- 3 replies
updated
a
collection
4 months ago
reacted to
mlabonne's
post with ๐
4 months ago
Post
6525
๐ LLM Course 2025 edition!
I updated the LLM Scientist roadmap and added a ton of new information and references. It covers training, datasets, evaluation, quantization, and new trends like test-time compute scaling.
The LLM Course has been incredibly popular (41.3k stars!) and I've been touched to receive many, many messages about how it helped people in their careers.
I know how difficult this stuff can be, so I'm super proud of the impact it had. I want to keep updating it in 2025, especially with the LLM Engineer roadmap.
Thanks everyone, hope you'll enjoy it!
๐ป LLM Course: https://huggingface.co/blog/mlabonne/llm-course
I updated the LLM Scientist roadmap and added a ton of new information and references. It covers training, datasets, evaluation, quantization, and new trends like test-time compute scaling.
The LLM Course has been incredibly popular (41.3k stars!) and I've been touched to receive many, many messages about how it helped people in their careers.
I know how difficult this stuff can be, so I'm super proud of the impact it had. I want to keep updating it in 2025, especially with the LLM Engineer roadmap.
Thanks everyone, hope you'll enjoy it!
๐ป LLM Course: https://huggingface.co/blog/mlabonne/llm-course
upvoted
an
article
4 months ago
Article
The Large Language Model Course
By
โข
โข
181
reacted to
as-cle-bert's
post with ๐ฅ
5 months ago
Post
2092
๐๐๐๐ซ๐ฅ๐ฒ ๐๐๐ฐ ๐๐๐๐ซ ๐ซ๐๐ฅ๐๐๐ฌ๐๐ฌ๐
Hi HuggingFacers๐ค, I decided to ship early this year, and here's what I came up with:
๐๐๐๐๐ญ๐๐จ๐ฐ๐ง (https://github.com/AstraBert/PdfItDown) - If you're like me, and you have all your RAG pipeline optimized for PDFs, but not for other data formats, here is your solution! With PdfItDown, you can convert Word documents, presentations, HTML pages, markdown sheets and (why not?) CSVs and XMLs in PDF format, for seamless integration with your RAG pipelines. Built upon MarkItDown by Microsoft
GitHub Repo ๐ https://github.com/AstraBert/PdfItDown
PyPi Package ๐ https://pypi.org/project/pdfitdown/
๐๐๐ง๐๐ซ๐๐ฏ ๐ฏ๐.๐.๐ (https://github.com/AstraBert/SenTrEv/tree/v1.0.0) - If you need to evaluate the ๐ฟ๐ฒ๐๐ฟ๐ถ๐ฒ๐๐ฎ๐น performance of your ๐๐ฒ๐ ๐ ๐ฒ๐บ๐ฏ๐ฒ๐ฑ๐ฑ๐ถ๐ป๐ด models, I have good news for you๐ฅณ๐ฅณ
The new release for ๐๐๐ง๐๐ซ๐๐ฏ now supports ๐ฑ๐ฒ๐ป๐๐ฒ and ๐๐ฝ๐ฎ๐ฟ๐๐ฒ retrieval (thanks to FastEmbed by Qdrant) with ๐๐ฒ๐ ๐-๐ฏ๐ฎ๐๐ฒ๐ฑ ๐ณ๐ถ๐น๐ฒ ๐ณ๐ผ๐ฟ๐บ๐ฎ๐๐ (.docx, .pptx, .csv, .html, .xml, .md, .pdf) and new ๐ฟ๐ฒ๐น๐ฒ๐๐ฎ๐ป๐ฐ๐ฒ ๐บ๐ฒ๐๐ฟ๐ถ๐ฐ๐!
GitHub repo ๐ https://github.com/AstraBert/SenTrEv
Release Notes ๐ https://github.com/AstraBert/SenTrEv/releases/tag/v1.0.0
PyPi Package ๐ https://pypi.org/project/sentrev/
Happy New Year and have fun!๐ฅ
Hi HuggingFacers๐ค, I decided to ship early this year, and here's what I came up with:
๐๐๐๐๐ญ๐๐จ๐ฐ๐ง (https://github.com/AstraBert/PdfItDown) - If you're like me, and you have all your RAG pipeline optimized for PDFs, but not for other data formats, here is your solution! With PdfItDown, you can convert Word documents, presentations, HTML pages, markdown sheets and (why not?) CSVs and XMLs in PDF format, for seamless integration with your RAG pipelines. Built upon MarkItDown by Microsoft
GitHub Repo ๐ https://github.com/AstraBert/PdfItDown
PyPi Package ๐ https://pypi.org/project/pdfitdown/
๐๐๐ง๐๐ซ๐๐ฏ ๐ฏ๐.๐.๐ (https://github.com/AstraBert/SenTrEv/tree/v1.0.0) - If you need to evaluate the ๐ฟ๐ฒ๐๐ฟ๐ถ๐ฒ๐๐ฎ๐น performance of your ๐๐ฒ๐ ๐ ๐ฒ๐บ๐ฏ๐ฒ๐ฑ๐ฑ๐ถ๐ป๐ด models, I have good news for you๐ฅณ๐ฅณ
The new release for ๐๐๐ง๐๐ซ๐๐ฏ now supports ๐ฑ๐ฒ๐ป๐๐ฒ and ๐๐ฝ๐ฎ๐ฟ๐๐ฒ retrieval (thanks to FastEmbed by Qdrant) with ๐๐ฒ๐ ๐-๐ฏ๐ฎ๐๐ฒ๐ฑ ๐ณ๐ถ๐น๐ฒ ๐ณ๐ผ๐ฟ๐บ๐ฎ๐๐ (.docx, .pptx, .csv, .html, .xml, .md, .pdf) and new ๐ฟ๐ฒ๐น๐ฒ๐๐ฎ๐ป๐ฐ๐ฒ ๐บ๐ฒ๐๐ฟ๐ถ๐ฐ๐!
GitHub repo ๐ https://github.com/AstraBert/SenTrEv
Release Notes ๐ https://github.com/AstraBert/SenTrEv/releases/tag/v1.0.0
PyPi Package ๐ https://pypi.org/project/sentrev/
Happy New Year and have fun!๐ฅ
- 2 replies
reacted to
awacke1's
post with ๐
5 months ago
Post
2697
LLMs and LRMs - Logical Reasoning and Chain of Thought.
This is a read-aloud lecture to answer questions of using language reasoning techniques in advanced AGI style chain of thought AI pipelines.
Produced using DeepResearchEvaluator located here: awacke1/DeepResearchEvaluator
Videos:
https://x.com/Aaron_Wacker/status/1874835790087463063
https://www.youtube.com/watch?v=fW_A1hH_7RM
This is a read-aloud lecture to answer questions of using language reasoning techniques in advanced AGI style chain of thought AI pipelines.
Produced using DeepResearchEvaluator located here: awacke1/DeepResearchEvaluator
Videos:
https://x.com/Aaron_Wacker/status/1874835790087463063
https://www.youtube.com/watch?v=fW_A1hH_7RM
- 1 reply
reacted to
cfahlgren1's
post with ๐
5 months ago
Post
3347
The
deepseek-ai/DeepSeek-V3 is very good! I have been playing with it and found it is really good at one-shotting a pretty good landing page.
You can play with it here: https://deepseek-artifacts.vercel.app
All the responses get saved in the cfahlgren1/react-code-instructions dataset. Hopefully we can build one of the biggest, highest quality frontend datasets on the hub ๐ช
You can play with it here: https://deepseek-artifacts.vercel.app
All the responses get saved in the cfahlgren1/react-code-instructions dataset. Hopefully we can build one of the biggest, highest quality frontend datasets on the hub ๐ช
reacted to
singhsidhukuldeep's
post with ๐
5 months ago
Post
3731
Exciting breakthrough in AI:
@Meta
's new Byte Latent Transformer (BLT) revolutionizes language models by eliminating tokenization!
The BLT architecture introduces a groundbreaking approach that processes raw bytes instead of tokens, achieving state-of-the-art performance while being more efficient and robust. Here's what makes it special:
>> Key Innovations
Dynamic Patching: BLT groups bytes into variable-sized patches based on entropy, allocating more compute power where the data is more complex. This results in up to 50% fewer FLOPs during inference compared to traditional token-based models.
Three-Component Architecture:
โข Lightweight Local Encoder that converts bytes to patch representations
โข Powerful Global Latent Transformer that processes patches
โข Local Decoder that converts patches back to bytes
>> Technical Advantages
โข Matches performance of Llama 3 at 8B parameters while being more efficient
โข Superior handling of non-English languages and rare character sequences
โข Remarkable 99.9% accuracy on spelling tasks
โข Better scaling properties than token-based models
>> Under the Hood
The system uses an entropy model to determine patch boundaries, cross-attention mechanisms for information flow, and hash n-gram embeddings for improved representation. The architecture allows simultaneous scaling of both patch and model size while maintaining fixed inference costs.
This is a game-changer for multilingual AI and could reshape how we build future language models. Excited to see how this technology evolves!
The BLT architecture introduces a groundbreaking approach that processes raw bytes instead of tokens, achieving state-of-the-art performance while being more efficient and robust. Here's what makes it special:
>> Key Innovations
Dynamic Patching: BLT groups bytes into variable-sized patches based on entropy, allocating more compute power where the data is more complex. This results in up to 50% fewer FLOPs during inference compared to traditional token-based models.
Three-Component Architecture:
โข Lightweight Local Encoder that converts bytes to patch representations
โข Powerful Global Latent Transformer that processes patches
โข Local Decoder that converts patches back to bytes
>> Technical Advantages
โข Matches performance of Llama 3 at 8B parameters while being more efficient
โข Superior handling of non-English languages and rare character sequences
โข Remarkable 99.9% accuracy on spelling tasks
โข Better scaling properties than token-based models
>> Under the Hood
The system uses an entropy model to determine patch boundaries, cross-attention mechanisms for information flow, and hash n-gram embeddings for improved representation. The architecture allows simultaneous scaling of both patch and model size while maintaining fixed inference costs.
This is a game-changer for multilingual AI and could reshape how we build future language models. Excited to see how this technology evolves!
- 3 replies
updated
a
collection
5 months ago
reacted to
clem's
post with ๐
5 months ago
Post
2126
Coming back to Paris Friday to open our new Hugging Face office!
We're at capacity for the party but add your name in the waiting list as we're trying to privatize the passage du Caire for extra space for robots ๐ค๐ฆพ๐ฆฟ
https://t.co/enkFXjWndJ
We're at capacity for the party but add your name in the waiting list as we're trying to privatize the passage du Caire for extra space for robots ๐ค๐ฆพ๐ฆฟ
https://t.co/enkFXjWndJ
- 1 reply