nyuuzyou PRO
nyuuzyou
AI & ML interests
None yet
Recent Activity
posted
an
update
1 day ago
š¼ļø PublicDomainFiles.com Collection - https://huggingface.co/datasets/nyuuzyou/publicdomainfiles
Collection of 206,204 Public Domain multimedia files featuring:
- Comprehensive metadata: title, description, creator name, keywords, original page URL, and more.
- Contains various media types including images, clip art, artwork, fonts, videos, and TV shows.
- All content explicitly released into the public domain under the CC0 license.
- Organized in a single `train` split with 206,204 entries.
Organizations
nyuuzyou's activity
posted
an
update
about 4 hours ago
reacted to
ginipick's
post with š„
1 day ago
Post
3944
š® Mistral Perflexity AI - Local LLM Space with Web Search Capabilities š
Hello AI enthusiasts! Today I'm excited to introduce my special Hugging Face space! š
ginigen/Mistral-Perflexity
āØ Key Features
Powerful Model: Using Private-BitSix-Mistral-Small-3.1-24B-Instruct-2503, optimized through 6-bit quantization to run smoothly on local 4090 GPUs! šŖ
Web Search Integration: Leveraging the Brave Search API to provide real-time web search results for user queries! š
Customizable Responses: Shape AI personality and response format through system messages āļø
Multilingual Support: Perfect handling of both English and Korean! šŗšøš°š·
š ļø Technical Highlights
GGUF Format: Optimized quantized model with excellent memory efficiency
Flash Attention: Applied optimization technology for faster inference speeds
8K Context Window: Capable of handling lengthy conversations and complex queries
Streaming Responses: Watch text being generated in real-time
š” Use Cases
Complex Q&A requiring real-time information
Programming assistance and code generation
Multilingual content creation and translation
Summarization and explanation of learning materials
š§ Customization
Adjust various parameters like Temperature, Top-p, Top-k, and repetition penalty to control response creativity and accuracy. Lower temperature (0.1-0.5) produces more deterministic responses, while higher values (0.7-1.0) generate more creative outputs!
š Try It Yourself!
This space is available for anyone to use for free. Experience the power of a robust local LLM combined with web search capabilities! Your feedback is always welcome! š
Hello AI enthusiasts! Today I'm excited to introduce my special Hugging Face space! š
ginigen/Mistral-Perflexity
āØ Key Features
Powerful Model: Using Private-BitSix-Mistral-Small-3.1-24B-Instruct-2503, optimized through 6-bit quantization to run smoothly on local 4090 GPUs! šŖ
Web Search Integration: Leveraging the Brave Search API to provide real-time web search results for user queries! š
Customizable Responses: Shape AI personality and response format through system messages āļø
Multilingual Support: Perfect handling of both English and Korean! šŗšøš°š·
š ļø Technical Highlights
GGUF Format: Optimized quantized model with excellent memory efficiency
Flash Attention: Applied optimization technology for faster inference speeds
8K Context Window: Capable of handling lengthy conversations and complex queries
Streaming Responses: Watch text being generated in real-time
š” Use Cases
Complex Q&A requiring real-time information
Programming assistance and code generation
Multilingual content creation and translation
Summarization and explanation of learning materials
š§ Customization
Adjust various parameters like Temperature, Top-p, Top-k, and repetition penalty to control response creativity and accuracy. Lower temperature (0.1-0.5) produces more deterministic responses, while higher values (0.7-1.0) generate more creative outputs!
š Try It Yourself!
This space is available for anyone to use for free. Experience the power of a robust local LLM combined with web search capabilities! Your feedback is always welcome! š
posted
an
update
1 day ago
Post
1538
š¼ļø PublicDomainFiles.com Collection -
nyuuzyou/publicdomainfiles
Collection of 206,204 Public Domain multimedia files featuring:
- Comprehensive metadata: title, description, creator name, keywords, original page URL, and more.
- Contains various media types including images, clip art, artwork, fonts, videos, and TV shows.
- All content explicitly released into the public domain under the CC0 license.
- Organized in a single
Collection of 206,204 Public Domain multimedia files featuring:
- Comprehensive metadata: title, description, creator name, keywords, original page URL, and more.
- Contains various media types including images, clip art, artwork, fonts, videos, and TV shows.
- All content explicitly released into the public domain under the CC0 license.
- Organized in a single
train split with 206,204 entries.
reacted to
openfree's
post with š„
1 day ago
Post
4052
š„ Creating a qwen3-30b-a3b / qwen3-235b-a22b Chatbot with Deep Research Capabilities š
openfree/qwen3-30b-a3b-research
openfree/qwen3-235b-a22b-research
Hello AI researchers! š Today I'm introducing a powerful chatbot implementation with real-time web search capabilities.
āØ Key Features
š§ Chatbot based on qwen3-30b-a3b and llama4-maverick models
š LLM-based optimal keyword extraction
š Real-time web search using SerpHouse API
š¬ Streaming responses for natural conversation experience
š ļø 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
š 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! š Leave your questions or suggestions in the comments! Let's improve it together~ šŖ
#LLM #ArtificialIntelligence #WebSearch #Gradio #DeepResearch #OpenSource
openfree/qwen3-30b-a3b-research
openfree/qwen3-235b-a22b-research
Hello AI researchers! š Today I'm introducing a powerful chatbot implementation with real-time web search capabilities.
āØ Key Features
š§ Chatbot based on qwen3-30b-a3b and llama4-maverick models
š LLM-based optimal keyword extraction
š Real-time web search using SerpHouse API
š¬ Streaming responses for natural conversation experience
š ļø 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
š 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! š Leave your questions or suggestions in the comments! Let's improve it together~ šŖ
#LLM #ArtificialIntelligence #WebSearch #Gradio #DeepResearch #OpenSource
updated
a
dataset
1 day ago
published
a
dataset
1 day ago
[bot] Conversion to Parquet
#1 opened 2 days ago
by
parquet-converter
updated
a
dataset
3 days ago
published
a
dataset
3 days ago
posted
an
update
3 days ago
Post
2040
š¼ļø OpenClipart SVG Dataset -
nyuuzyou/openclipart
Collection of 178,604 Public Domain Scalable Vector Graphics (SVG) clipart images featuring:
- Comprehensive metadata: title, description, artist name, tags, original page URL, and more.
- Contains complete SVG XML content (minified) for direct use or processing.
- All images explicitly released into the public domain under the CC0 license.
- Organized in a single
Collection of 178,604 Public Domain Scalable Vector Graphics (SVG) clipart images featuring:
- Comprehensive metadata: title, description, artist name, tags, original page URL, and more.
- Contains complete SVG XML content (minified) for direct use or processing.
- All images explicitly released into the public domain under the CC0 license.
- Organized in a single
train split with 178,604 entries.
[bot] Conversion to Parquet
#1 opened 4 days ago
by
parquet-converter
š© Report: Copyright infringement
8
127
#2 opened 27 days ago
by
no-mad
updated
a
dataset
4 days ago
published
a
dataset
4 days ago
updated
a
dataset
4 days ago
posted
an
update
4 days ago
Post
1377
š¼ļø Clker.com SVG Images Dataset -
nyuuzyou/clker-svg
Collection of 274,859 Public Domain Scalable Vector Graphics (SVG) clipart images featuring:
- Sourced from Clker.com, a platform for user-shared vector clipart
- Includes metadata: unique ID, title, tags, and original download URL
- Contains complete SVG XML content for direct use or processing
- All images explicitly released into the public domain under CC0 license
- Organized in a single train split with 274,859 entries
With nearly 275,000 public domain vector images, this represents one of the largest freely available SVG clipart collections on Hugging Face. While smaller than the SVGFind dataset, its public domain licensing makes it particularly valuable for commercial and unrestricted use cases without attribution requirements.
Collection of 274,859 Public Domain Scalable Vector Graphics (SVG) clipart images featuring:
- Sourced from Clker.com, a platform for user-shared vector clipart
- Includes metadata: unique ID, title, tags, and original download URL
- Contains complete SVG XML content for direct use or processing
- All images explicitly released into the public domain under CC0 license
- Organized in a single train split with 274,859 entries
With nearly 275,000 public domain vector images, this represents one of the largest freely available SVG clipart collections on Hugging Face. While smaller than the SVGFind dataset, its public domain licensing makes it particularly valuable for commercial and unrestricted use cases without attribution requirements.
Request on further scraping
2
#2 opened 5 days ago
by
mlinmg
published
a
dataset
5 days ago
[bot] Conversion to Parquet
#1 opened 5 days ago
by
parquet-converter
updated
a
dataset
5 days ago