Sailor2

community

Activity Feed Request to join this org

AI & ML interests

Open language models for South-East Asia

Recent Activity

wannaphong authored a paper 8 days ago

Mangosteen: An Open Thai Corpus for Language Model Pretraining

gabrielchua authored a paper 18 days ago

Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security

gabrielchua authored a paper 23 days ago

LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators

View all activity

Abhaykoul

posted an update 12 days ago

Post

3776

🚀 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.

🧠 What Makes Dhanishtha Special?
Unlike typical CoT models that only thinks one time, Dhanishtha thinks iteratively:

> Think → Answer → Rethink → Improve → Rethink again if needed.

🔗 Try it now: HelpingAI/Dhanishtha-2.0-preview-0825

🔞 Dhanishtha NSFW Preview

For those exploring more expressive and immersive roleplay scenarios, we’re also releasing:

HelpingAI/Dhanishtha-nsfw
A specialized version tuned for adult-themed interactions and character-driven roleplay.

🔗 Explore it here: HelpingAI/Dhanishtha-nsfw

💬 You can also try all of these live at chat.helpingai.co

4 replies

gabrielchua

authored a paper 18 days ago

Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security

Paper • 2507.19399 • Published 20 days ago • 1

gabrielchua

authored a paper 23 days ago

LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators

Paper • 2507.15339 • Published 25 days ago

gabrielchua

authored a paper 25 days ago

Toxicity-Aware Few-Shot Prompting for Low-Resource Singlish Translation

Paper • 2507.11966 • Published 30 days ago

SivilTaram

authored a paper 29 days ago

SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?

Paper • 2507.12415 • Published 29 days ago • 41

Abhaykoul

posted an update 30 days ago

Post

3036

🎉 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

🧠 What Makes Dhanishtha Different?
Unlike standard COT models that give one-shot responses, Dhanishtha thinks in layers:

> Think → Answer → Rethink → Improve → Rethink again if needed.

HelpingAI/Dhanishtha-2.0-preview-0725

gabrielchua

authored a paper about 1 month ago

Measuring What Matters: A Framework for Evaluating Safety Risks in Real-World LLM Applications

Paper • 2507.09820 • Published Jul 13

SivilTaram

authored a paper about 1 month ago

First Return, Entropy-Eliciting Explore

Paper • 2507.07017 • Published Jul 9 • 23

gabrielchua

authored a paper about 1 month ago

RabakBench: Scaling Human Annotations to Construct Localized Multilingual Safety Benchmarks for Low-Resource Languages

Paper • 2507.05980 • Published Jul 8 • 1

SivilTaram

authored a paper about 1 month ago

ZeCO: Zero Communication Overhead Sequence Parallelism for Linear Attention

Paper • 2507.01004 • Published Jul 1 • 10

Abhaykoul

posted an update about 1 month ago

Post

3008

🎉 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 blocks between responses.

🚀 Key Features
- Intermediate thinking: Think → Answer → Rethink → Answer → 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

1 reply

koalazf99

authored a paper about 2 months ago

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling

Paper • 2506.20512 • Published Jun 25 • 46

dreamerdeo

updated a Space about 2 months ago

README

💻

Abhaykoul

posted an update about 2 months ago

Post

4451

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:
🔑 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 ∫0∞𝑥3/𝑥−1𝑑𝑥 ?"}],
    stream=True,
    hide_think=False # Hide or show models thinking
)

for chunk in response:
    print(chunk.choices[0].delta.content, end="", flush=True)