John6666/femix-hassakuxl-v212-sdxl
Text-to-Image
โข
Updated
John Smith PRO
John6666
AI & ML interests
None yet
Recent Activity
published
a model
about 5 hours ago
John6666/femix-hassakuxl-v212-sdxl
published
a model
about 5 hours ago
John6666/samlust-nsfw-v12-sdxl
updated
a model
about 7 hours ago
John6666/samlust-nsfw-v12-sdxl
Organizations
John6666's activity
published
2
models
about 5 hours ago
updated
2
models
about 7 hours ago
liked
2
models
about 8 hours ago
reacted to
as-cle-bert's
post with ๐
about 8 hours ago
Post
303
Hey there, ๐ถ๐ป๐ด๐ฒ๐๐-๐ฎ๐ป๐๐๐ต๐ถ๐ป๐ด ๐๐ญ.๐ฌ.๐ฌ just dropped with major changes:
โ Embeddings: now works with Sentence Transformers, Jina AI, Cohere, OpenAI, and Model2Vec
All powered via ๐๐ต๐ผ๐ป๐ธ๐ถ๐ฒโ๐ ๐๐๐๐ผ๐๐บ๐ฏ๐ฒ๐ฑ๐ฑ๐ถ๐ป๐ด๐.
No more local-only limitations ๐
โ Vector DBs: now supports ๐ฎ๐น๐น ๐๐น๐ฎ๐บ๐ฎ๐๐ป๐ฑ๐ฒ๐ -๐ฐ๐ผ๐บ๐ฝ๐ฎ๐๐ถ๐ฏ๐น๐ฒ ๐ฏ๐ฎ๐ฐ๐ธ๐ฒ๐ป๐ฑ๐
Think: Qdrant, Pinecone, Weaviate, Milvus, etc.
No more bottlenecks๐
โ File parsing: now plugs into any ๐๐น๐ฎ๐บ๐ฎ๐๐ป๐ฑ๐ฒ๐ -๐ฐ๐ผ๐บ๐ฝ๐ฎ๐๐ถ๐ฏ๐น๐ฒ ๐ฑ๐ฎ๐๐ฎ ๐น๐ผ๐ฎ๐ฑ๐ฒ๐ฟ
Using LlamaParse, Docling or your own setup? Youโre covered.
Curious of knowing more? Try it out! ๐ https://github.com/AstraBert/ingest-anything
โ Embeddings: now works with Sentence Transformers, Jina AI, Cohere, OpenAI, and Model2Vec
All powered via ๐๐ต๐ผ๐ป๐ธ๐ถ๐ฒโ๐ ๐๐๐๐ผ๐๐บ๐ฏ๐ฒ๐ฑ๐ฑ๐ถ๐ป๐ด๐.
No more local-only limitations ๐
โ Vector DBs: now supports ๐ฎ๐น๐น ๐๐น๐ฎ๐บ๐ฎ๐๐ป๐ฑ๐ฒ๐ -๐ฐ๐ผ๐บ๐ฝ๐ฎ๐๐ถ๐ฏ๐น๐ฒ ๐ฏ๐ฎ๐ฐ๐ธ๐ฒ๐ป๐ฑ๐
Think: Qdrant, Pinecone, Weaviate, Milvus, etc.
No more bottlenecks๐
โ File parsing: now plugs into any ๐๐น๐ฎ๐บ๐ฎ๐๐ป๐ฑ๐ฒ๐ -๐ฐ๐ผ๐บ๐ฝ๐ฎ๐๐ถ๐ฏ๐น๐ฒ ๐ฑ๐ฎ๐๐ฎ ๐น๐ผ๐ฎ๐ฑ๐ฒ๐ฟ
Using LlamaParse, Docling or your own setup? Youโre covered.
Curious of knowing more? Try it out! ๐ https://github.com/AstraBert/ingest-anything
reacted to
ProCreations's
post with ๐
about 8 hours ago
Post
387
๐ง Post of the Day: Quantum AI โ Your Thoughts + Our Take
Yesterday we asked: โWhat will quantum computing do to AI?โ
Big thanks to solongeran for this poetic insight:
โQuantum computers are hard to run error-free. But once theyโre reliable, AI will be there. Safer than the daily sunset. Shure โ no more queues ;)โ
๐ Our Take โ What Quantum Computing Will Do to AI (by 2035)
By the time scalable, fault-tolerant quantum computers arrive, AI wonโt just run faster โ itโll evolve in ways weโve never seen:
โธป
๐น 1. Huge Speedups in Optimization & Search
Why: Quantum algorithms like Groverโs can cut down search and optimization times exponentially in some cases.
How: Theyโll power up tasks like hyperparameter tuning, decision-making in RL, and neural architecture search โ crunching what now takes hours into seconds.
โธป
๐น 2. Quantum Neural Networks (QNNs)
Why: QNNs can represent complex relationships more efficiently than classical nets.
How: They use entanglement and superposition to model rich feature spaces, especially useful for messy or high-dimensional data โ think drug discovery, finance, or even language structure.
โธป
๐น 3. Autonomous Scientific Discovery
Why: Quantum AI could simulate molecular systems that are impossible for classical computers.
How: By combining quantum simulation with AI exploration, we may unlock ultra-fast pathways to new drugs, materials, and technologies โ replacing years of lab work with minutes of computation.
โธป
๐น 4. Self-Evolving AI Architectures
Why: Future AI systems will design themselves.
How: Quantum processors will explore massive spaces of model variants in parallel, enabling AI to simulate, compare, and evolve new architectures โ fast, efficient, and with little trial-and-error.
โธป
โ๏ธ The Takeaway:
Quantum computing wonโt just speed up AI. Itโll open doors to new types of intelligence โ ones that learn, discover, and evolve far beyond todayโs limits.
Yesterday we asked: โWhat will quantum computing do to AI?โ
Big thanks to solongeran for this poetic insight:
โQuantum computers are hard to run error-free. But once theyโre reliable, AI will be there. Safer than the daily sunset. Shure โ no more queues ;)โ
๐ Our Take โ What Quantum Computing Will Do to AI (by 2035)
By the time scalable, fault-tolerant quantum computers arrive, AI wonโt just run faster โ itโll evolve in ways weโve never seen:
โธป
๐น 1. Huge Speedups in Optimization & Search
Why: Quantum algorithms like Groverโs can cut down search and optimization times exponentially in some cases.
How: Theyโll power up tasks like hyperparameter tuning, decision-making in RL, and neural architecture search โ crunching what now takes hours into seconds.
โธป
๐น 2. Quantum Neural Networks (QNNs)
Why: QNNs can represent complex relationships more efficiently than classical nets.
How: They use entanglement and superposition to model rich feature spaces, especially useful for messy or high-dimensional data โ think drug discovery, finance, or even language structure.
โธป
๐น 3. Autonomous Scientific Discovery
Why: Quantum AI could simulate molecular systems that are impossible for classical computers.
How: By combining quantum simulation with AI exploration, we may unlock ultra-fast pathways to new drugs, materials, and technologies โ replacing years of lab work with minutes of computation.
โธป
๐น 4. Self-Evolving AI Architectures
Why: Future AI systems will design themselves.
How: Quantum processors will explore massive spaces of model variants in parallel, enabling AI to simulate, compare, and evolve new architectures โ fast, efficient, and with little trial-and-error.
โธป
โ๏ธ The Takeaway:
Quantum computing wonโt just speed up AI. Itโll open doors to new types of intelligence โ ones that learn, discover, and evolve far beyond todayโs limits.
reacted to
vincentg64's
post with ๐
about 8 hours ago
Post
366
How to Design LLMs that Donโt Need Prompt Engineering https://mltblog.com/3GAbAQu
Standard LLMs rely on prompt engineering to fix problems (hallucinations, poor response, missing information) that come from issues in the backend architecture. If the backend (corpus processing) is properly built from the ground up, it is possible to offer a full, comprehensive answer to a meaningful prompt, without the need for multiple prompts, rewording your query, having to go through a chat session, or prompt engineering. In this article, I explain how to do it, focusing on enterprise corpuses. The strategy relies on four principles:
โก๏ธ Exact and augmented retrieval
โก๏ธ Showing full context in the response
โก๏ธ Enhanced UI with option menu
โก๏ธ Structured response as opposed to long text
I now explain these principles.
Read full article at https://mltblog.com/3GAbAQu
#xLLM #BondingAI #PromptEngineering
Standard LLMs rely on prompt engineering to fix problems (hallucinations, poor response, missing information) that come from issues in the backend architecture. If the backend (corpus processing) is properly built from the ground up, it is possible to offer a full, comprehensive answer to a meaningful prompt, without the need for multiple prompts, rewording your query, having to go through a chat session, or prompt engineering. In this article, I explain how to do it, focusing on enterprise corpuses. The strategy relies on four principles:
โก๏ธ Exact and augmented retrieval
โก๏ธ Showing full context in the response
โก๏ธ Enhanced UI with option menu
โก๏ธ Structured response as opposed to long text
I now explain these principles.
Read full article at https://mltblog.com/3GAbAQu
#xLLM #BondingAI #PromptEngineering
published
5
models
about 8 hours ago
John6666/donuts-delivery-mix-v4-v41-sdxl
Text-to-Image
โข
Updated
John6666/nova-anime-xl-il-v70-sdxl
Text-to-Image
โข
Updated
John6666/one-obsession-noob-v035-mature-epsa-sdxl
Text-to-Image
โข
Updated
John6666/real-illustrious-test-sdxl
Text-to-Image
โข
Updated
John6666/xepernoobhax-005epsilon-ti-sdxl
Text-to-Image
โข
Updated
updated
a
model
about 10 hours ago
liked
2
models
about 10 hours ago
updated
a
model
about 10 hours ago
liked
a
model
about 10 hours ago
