Article
How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications
Dharma-AI
• • 38
Equinox Elahin
EquinoxElahin
AI & ML interests
None yet
Recent Activity
upvoted an article 3 months ago
Beyond LoRA: Can you beat the most popular fine-tuning technique? reacted to prithivMLmods's post with 🔥 9 months ago
Introducing the Qwen-Image-Edit-3D-Lighting-Control app, featuring 8× horizontal and 3× elevational lighting positions for precise 3D lighting control. It enables studio-level lighting using fast Qwen Image Edit fast inference, paired with Multi-Angle-Lighting adapters. 🔦
🔥 Space: https://huggingface.co/spaces/prithivMLmods/Qwen-Image-Edit-3D-Lighting-Control
✅ Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
📂 GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-Edit-3D-Lighting-ControlOrganizations
None yet
upvoted an article 12 days ago
upvoted an article 3 months ago
Article
Beyond LoRA: Can you beat the most popular fine-tuning technique?
- +2
BenjaminB, sayakpaul, hubnemo, kashif
• • 109 reacted to prithivMLmods's post with 🔥 9 months ago
Post
2,345
Introducing the Qwen-Image-Edit-3D-Lighting-Control app, featuring 8× horizontal and 3× elevational lighting positions for precise 3D lighting control. It enables studio-level lighting using fast Qwen Image Edit fast inference, paired with Multi-Angle-Lighting adapters. 🔦
🔥 Space: prithivMLmods/Qwen-Image-Edit-3D-Lighting-Control
✅ Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
📂 GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-Edit-3D-Lighting-Control
🔥 Space: prithivMLmods/Qwen-Image-Edit-3D-Lighting-Control
✅ Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
📂 GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-Edit-3D-Lighting-Control
upvoted 2
articles 10 months ago
Article
AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems
ServiceNow-AI
• • 51 Article
Open Responses: What you need to know
- +2
evalstate, burtenshaw, merve, pcuenq
• • 114 upvoted an article 11 months ago
Article
Codex is Open Sourcing AI models
burtenshaw, evalstate
• • 85 upvoted a paper 11 months ago
upvoted 4
articles 12 months ago
Article
KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 439 Article
KV Cache from scratch in nanoVLM
- +3
ariG23498, kashif, lusxvr, andito, pcuenq
• • 121 Article
Continuous batching from first principles
- +1
ror, ArthurZ, mcpotato
• • 462 Article
Projected Abliteration
grimjim
• • 47 liked a
Space about 1 year ago
upvoted 2
articles about 1 year ago
Article
There is no such thing as a tokenizer-free lunch
catherinearnett
• • 103 Article
Implementing MCP Servers in Python: An AI Shopping Assistant with Gradio
freddyaboulton
• • 60 upvoted an article over 1 year ago
Article
Ettin Suite: SoTA Paired Encoders and Decoders
- +4
orionweller, kdricci, mmarone, NohTow, dlawrie, vandurme
• • 84 reacted to jasoncorkill's post with 😎 over 1 year ago
Post
3,296
"Why did the bee get married?"
"Because he found his honey!"
This was the "funniest" joke out of 10'000 jokes we generated with LLMs. With 68% of respondents rating it as "funny".
Original jokes are particularly hard for LLMs, as jokes are very nuanced and a lot of context is needed to understand if something is "funny". Something that can only reliably be measured using humans.
LLMs are not equally good at generating jokes in every language. Generated English jokes turned out to be way funnier than the Japanese ones. 46% of English-speaking voters on average found the generated joke funny. The same statistic for other languages:
Vietnamese: 44%
Portuguese: 40%
Arabic: 37%
Japanese: 28%
There is not much variance in generation quality among models for any fixed language. But still Claude Sonnet 4 slightly outperforms others in Vietnamese, Arabic and Japanese and Gemini 2.5 Flash in Portuguese and English
We have release the 1 Million (!) native speaker ratings and the 10'000 jokes as a dataset for anyone to use:
Rapidata/multilingual-llm-jokes-4o-claude-gemini
"Because he found his honey!"
This was the "funniest" joke out of 10'000 jokes we generated with LLMs. With 68% of respondents rating it as "funny".
Original jokes are particularly hard for LLMs, as jokes are very nuanced and a lot of context is needed to understand if something is "funny". Something that can only reliably be measured using humans.
LLMs are not equally good at generating jokes in every language. Generated English jokes turned out to be way funnier than the Japanese ones. 46% of English-speaking voters on average found the generated joke funny. The same statistic for other languages:
Vietnamese: 44%
Portuguese: 40%
Arabic: 37%
Japanese: 28%
There is not much variance in generation quality among models for any fixed language. But still Claude Sonnet 4 slightly outperforms others in Vietnamese, Arabic and Japanese and Gemini 2.5 Flash in Portuguese and English
We have release the 1 Million (!) native speaker ratings and the 10'000 jokes as a dataset for anyone to use:
Rapidata/multilingual-llm-jokes-4o-claude-gemini
- 7 replies
upvoted an article over 1 year ago
Article
Transformers Are Getting Old: Variants and Alternatives Exist!
ProCreations
• • 46 reacted to Jaward's post with 👀 over 1 year ago
Post
1,873
Funtime with SpatialLM- eventually it will serve well in embodied AI.
reacted to singhsidhukuldeep's post with 🔥 over 1 year ago
Post
7,285
Exciting New Tool for Knowledge Graph Extraction from Plain Text!
I just came across a groundbreaking new tool called KGGen that's solving a major challenge in the AI world - the scarcity of high-quality knowledge graph data.
KGGen is an open-source Python package that leverages language models to extract knowledge graphs (KGs) from plain text. What makes it special is its innovative approach to clustering related entities, which significantly reduces sparsity in the extracted KGs.
The technical approach is fascinating:
1. KGGen uses a multi-stage process involving an LLM (GPT-4o in their implementation) to extract entities and relations from source text
2. It aggregates graphs across sources to reduce redundancy
3. Most importantly, it applies iterative LM-based clustering to refine the raw graph
The clustering stage is particularly innovative - it identifies which nodes and edges refer to the same underlying entities or concepts. This normalizes variations in tense, plurality, stemming, and capitalization (e.g., "labors" clustered with "labor").
The researchers from Stanford and University of Toronto also introduced MINE (Measure of Information in Nodes and Edges), the first benchmark for evaluating KG extractors. When tested against existing methods like OpenIE and GraphRAG, KGGen outperformed them by up to 18%.
For anyone working with knowledge graphs, RAG systems, or KG embeddings, this tool addresses the fundamental challenge of data scarcity that's been holding back progress in graph-based foundation models.
The package is available via pip install kg-gen, making it accessible to everyone. This could be a game-changer for knowledge graph applications!
I just came across a groundbreaking new tool called KGGen that's solving a major challenge in the AI world - the scarcity of high-quality knowledge graph data.
KGGen is an open-source Python package that leverages language models to extract knowledge graphs (KGs) from plain text. What makes it special is its innovative approach to clustering related entities, which significantly reduces sparsity in the extracted KGs.
The technical approach is fascinating:
1. KGGen uses a multi-stage process involving an LLM (GPT-4o in their implementation) to extract entities and relations from source text
2. It aggregates graphs across sources to reduce redundancy
3. Most importantly, it applies iterative LM-based clustering to refine the raw graph
The clustering stage is particularly innovative - it identifies which nodes and edges refer to the same underlying entities or concepts. This normalizes variations in tense, plurality, stemming, and capitalization (e.g., "labors" clustered with "labor").
The researchers from Stanford and University of Toronto also introduced MINE (Measure of Information in Nodes and Edges), the first benchmark for evaluating KG extractors. When tested against existing methods like OpenIE and GraphRAG, KGGen outperformed them by up to 18%.
For anyone working with knowledge graphs, RAG systems, or KG embeddings, this tool addresses the fundamental challenge of data scarcity that's been holding back progress in graph-based foundation models.
The package is available via pip install kg-gen, making it accessible to everyone. This could be a game-changer for knowledge graph applications!
reacted to burtenshaw's post with 🔥 over 1 year ago
Post
6,565
Now the Hugging Face agent course is getting real! With frameworks like smolagents, LlamaIndex, and LangChain.
🔗 Follow the org for updates
agents-course
This week we are releasing the first framework unit in the course and it’s on smolagents. This is what the unit covers:
- why should you use smolagents vs another library?
- how to build agents that use code
- build multiagents systems
- use vision language models for browser use
The team has been working flat out on this for a few weeks. Led by @sergiopaniego and supported by smolagents author @m-ric .
🔗 Follow the org for updates
This week we are releasing the first framework unit in the course and it’s on smolagents. This is what the unit covers:
- why should you use smolagents vs another library?
- how to build agents that use code
- build multiagents systems
- use vision language models for browser use
The team has been working flat out on this for a few weeks. Led by @sergiopaniego and supported by smolagents author @m-ric .