Zero-shot World Models Are Developmentally Efficient Learners
Paper โข 2604.10333 โข Published โข 7
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Sparse Reward Subsystem in Large Language Models
Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
awwklย
submitted a
paper to Daily Papers 6 days ago
Xkevย
submitted a
paper to Daily Papers 3 months ago
thubZ9ย
authored a
paper 6 months ago
Asap7772ย
authored 3
papers 7 months ago
Personalized Preference Fine-tuning of Diffusion Models
Paper โข 2501.06655 โข Published โข 1
Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models
Paper โข 2502.17387 โข Published โข 7
RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
Paper โข 2510.02263 โข Published โข 9
AnSungJae3489ย
posted an update 7 months ago
Post
2632
ShareGPT? How about ShareGPT-X?
We release **92K** Human with LLM conversations as a refresh and update over the original ShareGPT Dataset.
DSULT-Core/ShareGPT-X
We release **92K** Human with LLM conversations as a refresh and update over the original ShareGPT Dataset.
DSULT-Core/ShareGPT-X
Post
3339
๐ Ever dreamed of training your own Large Language Model from scratch? What if I told you it doesn't require a supercomputer or PhD in ML? ๐คฏ
Introducing LLM Trainer - the educational framework that makes LLM training accessible to EVERYONE! Whether you're on a CPU-only laptop or scaling to distributed GPUs, we've got you covered. ๐ปโก๏ธ๐ฅ๏ธ
Why LLM Trainer? Because existing tools are either too simplistic (hiding the magic) or too complex (requiring expert knowledge). We bridge the gap with:
๐ Educational transparency - every component built from scratch with clear code
๐ป CPU-first approach - start training immediately, no GPU needed
๐ง Full customization - modify anything you want
๐ Seamless scaling - from laptop to cluster without code changes
๐ค HuggingFace integration - works with existing models & tokenizers
Key highlights:
โ Built-in tokenizers (BPE, WordPiece, HF wrappers)
โ Complete Transformer implementation from scratch
โ Optimized for CPU training
โ Advanced features: mixed precision, gradient checkpointing, multiple generation strategies
โ Comprehensive monitoring & metrics
Perfect for:
- Students learning transformers
- Researchers prototyping new ideas
- Developers building domain-specific models
Ready to train your first LLM? It's easier than you think!
๐ Check it out: https://github.com/HelpingAI/llm-trainer
๐ Docs: Getting Started Guide
๐ฌ Join the community: GitHub Discussions
#AI #MachineLearning #LLM #DeepLearning #OpenSource #Python #HuggingFace #NLP
Special thanks to HuggingFace and PyTorch teams for the amazing ecosystem! ๐
Introducing LLM Trainer - the educational framework that makes LLM training accessible to EVERYONE! Whether you're on a CPU-only laptop or scaling to distributed GPUs, we've got you covered. ๐ปโก๏ธ๐ฅ๏ธ
Why LLM Trainer? Because existing tools are either too simplistic (hiding the magic) or too complex (requiring expert knowledge). We bridge the gap with:
๐ Educational transparency - every component built from scratch with clear code
๐ป CPU-first approach - start training immediately, no GPU needed
๐ง Full customization - modify anything you want
๐ Seamless scaling - from laptop to cluster without code changes
๐ค HuggingFace integration - works with existing models & tokenizers
Key highlights:
โ Built-in tokenizers (BPE, WordPiece, HF wrappers)
โ Complete Transformer implementation from scratch
โ Optimized for CPU training
โ Advanced features: mixed precision, gradient checkpointing, multiple generation strategies
โ Comprehensive monitoring & metrics
Perfect for:
- Students learning transformers
- Researchers prototyping new ideas
- Developers building domain-specific models
Ready to train your first LLM? It's easier than you think!
๐ Check it out: https://github.com/HelpingAI/llm-trainer
๐ Docs: Getting Started Guide
๐ฌ Join the community: GitHub Discussions
#AI #MachineLearning #LLM #DeepLearning #OpenSource #Python #HuggingFace #NLP
Special thanks to HuggingFace and PyTorch teams for the amazing ecosystem! ๐
- 1 reply
kzliuย
authored a
paper 8 months ago
Post
4173
๐ Dhanishtha-2.0-preview-0825 Is Here
The Intermediate Thinking Model just leveled up again.
With sharper reasoning, better tool use, and expanded capabilities, Dhanishtha-2.0-preview-0825 is now live and ready to impress.
๐ง What Makes Dhanishtha Special?
Unlike typical CoT models that only thinks one time, Dhanishtha thinks iteratively:
> Think โ Answer โ Rethink โ Improve โ Rethink again if needed.
๐ Try it now: HelpingAI/Dhanishtha-2.0-preview-0825
๐ Dhanishtha NSFW Preview
For those exploring more expressive and immersive roleplay scenarios, weโre also releasing:
HelpingAI/Dhanishtha-nsfw
A specialized version tuned for adult-themed interactions and character-driven roleplay.
๐ Explore it here: HelpingAI/Dhanishtha-nsfw
๐ฌ You can also try all of these live at chat.helpingai.co
The Intermediate Thinking Model just leveled up again.
With sharper reasoning, better tool use, and expanded capabilities, Dhanishtha-2.0-preview-0825 is now live and ready to impress.
๐ง What Makes Dhanishtha Special?
Unlike typical CoT models that only thinks one time, Dhanishtha thinks iteratively:
> Think โ Answer โ Rethink โ Improve โ Rethink again if needed.
๐ Try it now: HelpingAI/Dhanishtha-2.0-preview-0825
๐ Dhanishtha NSFW Preview
For those exploring more expressive and immersive roleplay scenarios, weโre also releasing:
HelpingAI/Dhanishtha-nsfw
A specialized version tuned for adult-themed interactions and character-driven roleplay.
๐ Explore it here: HelpingAI/Dhanishtha-nsfw
๐ฌ You can also try all of these live at chat.helpingai.co
- 4 replies
Post
3167
๐ Dhanishtha-2.0-preview-0725 is Now Live
The Intermediate Thinking Model just got even better.
With the new update, Dhanishtha is now sharper, smarter, and trained further on tool use
๐ง What Makes Dhanishtha Different?
Unlike standard COT models that give one-shot responses, Dhanishtha thinks in layers:
> Think โ Answer โ Rethink โ Improve โ Rethink again if needed.
HelpingAI/Dhanishtha-2.0-preview-0725
The Intermediate Thinking Model just got even better.
With the new update, Dhanishtha is now sharper, smarter, and trained further on tool use
๐ง What Makes Dhanishtha Different?
Unlike standard COT models that give one-shot responses, Dhanishtha thinks in layers:
> Think โ Answer โ Rethink โ Improve โ Rethink again if needed.
HelpingAI/Dhanishtha-2.0-preview-0725
Post
3125
๐ Dhanishtha 2.0 Preview is Now Open Source!
The world's first Intermediate Thinking Model is now available to everyone!
Dhanishtha 2.0 Preview brings revolutionary intermediate thinking capabilities to the open-source community. Unlike traditional reasoning models that think once, Dhanishtha can think, answer, rethink, answer again, and continue rethinking as needed using multiple
๐ Key Features
- Intermediate thinking: Think โ Answer โ Rethink โ Answer โ Rethink if needed...
- Token efficient: Uses up to 79% fewer tokens than DeepSeek R1 on similar queries
- Transparent thinking: See the model's reasoning process in real-time
- Open source: Freely available for research and development
HelpingAI/Dhanishtha-2.0-preview
https://helpingai.co/chat
The world's first Intermediate Thinking Model is now available to everyone!
Dhanishtha 2.0 Preview brings revolutionary intermediate thinking capabilities to the open-source community. Unlike traditional reasoning models that think once, Dhanishtha can think, answer, rethink, answer again, and continue rethinking as needed using multiple
๐ Key Features
- Intermediate thinking: Think โ Answer โ Rethink โ Answer โ Rethink if needed...
- Token efficient: Uses up to 79% fewer tokens than DeepSeek R1 on similar queries
- Transparent thinking: See the model's reasoning process in real-time
- Open source: Freely available for research and development
HelpingAI/Dhanishtha-2.0-preview
https://helpingai.co/chat
- 2 replies
Post
4688
Introducing Dhanishtha 2.0: World's first Intermediate Thinking Model
Dhanishtha 2.0 is the world's first LLM designed to think between the responses. Unlike other Reasoning LLMs, which think just once.
Dhanishtha can think, rethink, self-evaluate, and refine in between responses using multiple <think> blocks.
This technique makes it Hinghlt Token efficient it Uses up to 79% fewer tokens than DeepSeek R1
---
You can try our model from: https://helpingai.co/chat
Also, we're gonna Open-Source Dhanistha on July 1st.
---
For Devs:
๐ Get your API key at https://helpingai.co/dashboard
Dhanishtha 2.0 is the world's first LLM designed to think between the responses. Unlike other Reasoning LLMs, which think just once.
Dhanishtha can think, rethink, self-evaluate, and refine in between responses using multiple <think> blocks.
This technique makes it Hinghlt Token efficient it Uses up to 79% fewer tokens than DeepSeek R1
---
You can try our model from: https://helpingai.co/chat
Also, we're gonna Open-Source Dhanistha on July 1st.
---
For Devs:
๐ Get your API key at https://helpingai.co/dashboard
from HelpingAI import HAI # pip install HelpingAI==1.1.1
from rich import print
hai = HAI(api_key="hl-***********************")
response = hai.chat.completions.create(
model="Dhanishtha-2.0-preview",
messages=[{"role": "user", "content": "What is the value of โซ0โ๐ฅ3/๐ฅโ1๐๐ฅ ?"}],
stream=True,
hide_think=False # Hide or show models thinking
)
for chunk in response:
print(chunk.choices[0].delta.content, end="", flush=True)
- 2 replies
siddharthmbย
authored a
paper 11 months ago
yuegaoย
authored a
paper 11 months ago
Kameshrย
updated a
dataset about 1 year ago
Kameshrย
published a
dataset about 1 year ago
yuegaoย
authored a
paper about 1 year ago
Asap7772ย
authored a
paper about 1 year ago
ayushchakravarthyย
authored a
paper about 1 year ago