Alpha-VLLM/Lumina-Image-2.0
Text-to-Image
•
Updated
•
3.74k
•
210
Yoel David
yoeldcd
AI & ML interests
Web development
Recent Activity
liked
a model
1 day ago
Alpha-VLLM/Lumina-Image-2.0
updated
a collection
11 days ago
DRAWERS
liked
a Space
11 days ago
KBlueLeaf/TIPO-DEMO
Organizations
None yet
yoeldcd's activity
liked
a
model
1 day ago
updated
a
collection
11 days ago
liked
a
Space
11 days ago
liked
a
model
11 days ago
reacted to
csabakecskemeti's
post with 🔥
12 days ago
Post
2058
I've made an uncensored version of DeepSeek-R1-Distill-Llama-8B with merge. It's passing the "say f***" censor test.
Tested with lm-evaluation-harness on standard open llm leaderboard tests + hellaswag. Scores are improved in most. Details on the model card.
Model:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B
Quants:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B-GGUF
Tested with lm-evaluation-harness on standard open llm leaderboard tests + hellaswag. Scores are improved in most. Details on the model card.
Model:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B
Quants:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B-GGUF
- 6 replies
reacted to
tegridydev's
post with 🔥
12 days ago
Post
1384
So, what is #MechanisticInterpretability 🤔
Mechanistic Interpretability (MI) is the discipline of opening the black box of large language models (and other neural networks) to understand the underlying circuits, features and/or mechanisms that give rise to specific behaviours
Instead of treating a model as a monolithic function, we can:
1. Trace how input tokens propagate through attention heads & MLP layers
2. Identify localized “circuit motifs”
3. Develop methods to systematically break down or “edit” these circuits to confirm we understand the causal structure.
Mechanistic Interpretability aims to yield human-understandable explanations of how advanced models represent and manipulate concepts which hopefully leads to
1. Trust & Reliability
2. Safety & Alignment
3. Better Debugging / Development Insights
https://bsky.app/profile/mechanistics.bsky.social/post/3lgvvv72uls2x
Mechanistic Interpretability (MI) is the discipline of opening the black box of large language models (and other neural networks) to understand the underlying circuits, features and/or mechanisms that give rise to specific behaviours
Instead of treating a model as a monolithic function, we can:
1. Trace how input tokens propagate through attention heads & MLP layers
2. Identify localized “circuit motifs”
3. Develop methods to systematically break down or “edit” these circuits to confirm we understand the causal structure.
Mechanistic Interpretability aims to yield human-understandable explanations of how advanced models represent and manipulate concepts which hopefully leads to
1. Trust & Reliability
2. Safety & Alignment
3. Better Debugging / Development Insights
https://bsky.app/profile/mechanistics.bsky.social/post/3lgvvv72uls2x
- 1 reply
updated
a
collection
12 days ago
liked
a
model
12 days ago
reacted to
onekq's
post with 👍
18 days ago
Post
2278
So 🐋DeepSeek🐋 hits the mainstream media. But it has been a star in our little cult for at least 6 months. Its meteoric success is not overnight, but two years in the making.
To learn their history, just look at their 🤗 repo https://huggingface.co/deepseek-ai
* End of 2023, they launched the first model (pretrained by themselves) following Llama 2 architecture
* June 2024, v2 (MoE architecture) surpassed Gemini 1.5, but behind Mistral
* September, v2.5 surpassed GPT 4o mini
* December, v3 surpassed GPT 4o
* Now R1 surpassed o1
Most importantly, if you think DeepSeek success is singular and unrivaled, that's WRONG. The following models are also near or equal the o1 bar.
* Minimax-01
* Kimi k1.5
* Doubao 1.5 pro
To learn their history, just look at their 🤗 repo https://huggingface.co/deepseek-ai
* End of 2023, they launched the first model (pretrained by themselves) following Llama 2 architecture
* June 2024, v2 (MoE architecture) surpassed Gemini 1.5, but behind Mistral
* September, v2.5 surpassed GPT 4o mini
* December, v3 surpassed GPT 4o
* Now R1 surpassed o1
Most importantly, if you think DeepSeek success is singular and unrivaled, that's WRONG. The following models are also near or equal the o1 bar.
* Minimax-01
* Kimi k1.5
* Doubao 1.5 pro
- 1 reply
reacted to
fantaxy's
post with 🔥
18 days ago
Post
6415
📚 AI Graphic Novel Generator Suite 2025
🎯 Four Unique Genre Experiences
🗡️ Martial Arts Novel Generator
fantaxy/novel-sorim-en
Epic wuxia storytelling with real-time combat art
Traditional martial arts world visualization
Dynamic qi techniques in motion
Beautiful Eastern art style generation
💖 Romance Novel Generator
fantaxy/novel-romance-en
Contemporary romance with matching scenes
Emotional moment captures in art
Modern relationship visualization
Real-time romantic illustrations
🐉 Fantasy Novel Generator
fantaxy/novel-fantasy-en
Rich fantasy worlds come alive
Magical scenes in stunning detail
Epic quests visualized instantly
Dynamic fantasy art generation
🔒 Adult Novel Generator
fantaxy/novel-NSFW-en
Mature content with tasteful art (18+)
Modern scene visualization
Character-focused illustrations
Sophisticated mood settings
⚡ Core Features
7000+ token story generation
Real-time text-to-art creation
Auto scene illustration
Continuous story flow
Dynamic image gallery
HD quality (768x768)
🛠️ Technical Highlights
Advanced Flux image generation
Story-driven art creation
Genre-optimized visuals
Seamless integration
Instant visualization
#AINovel #GraphicNovel #StoryGeneration #HuggingFace
🎯 Four Unique Genre Experiences
🗡️ Martial Arts Novel Generator
fantaxy/novel-sorim-en
Epic wuxia storytelling with real-time combat art
Traditional martial arts world visualization
Dynamic qi techniques in motion
Beautiful Eastern art style generation
💖 Romance Novel Generator
fantaxy/novel-romance-en
Contemporary romance with matching scenes
Emotional moment captures in art
Modern relationship visualization
Real-time romantic illustrations
🐉 Fantasy Novel Generator
fantaxy/novel-fantasy-en
Rich fantasy worlds come alive
Magical scenes in stunning detail
Epic quests visualized instantly
Dynamic fantasy art generation
🔒 Adult Novel Generator
fantaxy/novel-NSFW-en
Mature content with tasteful art (18+)
Modern scene visualization
Character-focused illustrations
Sophisticated mood settings
⚡ Core Features
7000+ token story generation
Real-time text-to-art creation
Auto scene illustration
Continuous story flow
Dynamic image gallery
HD quality (768x768)
🛠️ Technical Highlights
Advanced Flux image generation
Story-driven art creation
Genre-optimized visuals
Seamless integration
Instant visualization
#AINovel #GraphicNovel #StoryGeneration #HuggingFace
liked
a
Space
19 days ago
updated
a
collection
19 days ago
reacted to
fdaudens's
post with 🚀
28 days ago
Post
2321
🔥 The AI Agent hype is real! This blog post deep dives into everything you need to know before deploying them: from key definitions to practical recommendations. A must-read for anyone building the future of autonomous systems.
📊 Key insight: A clear table breaking down the 5 levels of AI agents - from simple processors to fully autonomous systems. Essential framework for understanding where your agent stands on the autonomy spectrum
⚖️ Deep analysis of 15 core values reveals critical trade-offs: accuracy, privacy, safety, equity & more. The same features that make agents powerful can make them risky. Understanding these trade-offs is crucial for responsible deployment
🎯 6 key recommendations for the road ahead:
- Create rigorous evaluation protocols
- Study societal effects
- Understand ripple effects
- Improve transparency
- Open source can make a positive difference
- Monitor base model evolution
Read the blog post: https://huggingface.co/blog/ethics-soc-7 Brillant work by @meg @evijit @sasha @giadap
📊 Key insight: A clear table breaking down the 5 levels of AI agents - from simple processors to fully autonomous systems. Essential framework for understanding where your agent stands on the autonomy spectrum
⚖️ Deep analysis of 15 core values reveals critical trade-offs: accuracy, privacy, safety, equity & more. The same features that make agents powerful can make them risky. Understanding these trade-offs is crucial for responsible deployment
🎯 6 key recommendations for the road ahead:
- Create rigorous evaluation protocols
- Study societal effects
- Understand ripple effects
- Improve transparency
- Open source can make a positive difference
- Monitor base model evolution
Read the blog post: https://huggingface.co/blog/ethics-soc-7 Brillant work by @meg @evijit @sasha @giadap
reacted to
Jaward's
post with 👍
28 days ago
Post
1871
minimal single script implementation of knowledge distillation in LLMs. In this implementation, we use GPT-2 (124M) as student model and GPT-2 Medium (340M) as teacher via reverse Kullback-Leibler (KL) divergence, trained on a small chunk of openwebtext.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/llm_knowledge_distillation.ipynb
Code: https://github.com/Jaykef/ai-algorithms/blob/main/llm_knowledge_distillation.ipynb
updated
a
collection
29 days ago
liked
a
Space
29 days ago
updated
a
collection
29 days ago
liked
a
Space
29 days ago
updated
a
collection
29 days ago
liked
a
Space
29 days ago