Dango233 (@dango233max) 's Twitter Profile
Dango233

@dango233max

Baking open AI system
Garnishing open weights

github.com/Dango233/

ID: 402566466

calendar_today01-11-2011 08:17:43

132 Tweet

876 Takipçi

292 Takip Edilen

Stable Diffusion (@stablediffusion) 's Twitter Profile Photo

Hi there, Stability AI here. We’re working on getting access back to our official account. Please don’t click any links and we’ll be back shortly!

Tanishq Mathew Abraham, Ph.D. (@iscienceluvr) 's Twitter Profile Photo

Anyone who thinks DeepSeek just came out of nowhere should see this graph. For each model on this graph, weights, code, and detailed papers were released. This is a team with a strong track record and has been working hard for a while. They didn't come out of nowhere.

Anyone who thinks DeepSeek just came out of nowhere should see this graph.

For each model on this graph, weights, code, and detailed papers were released.

This is a team with a strong track record and has been working hard for a while. They didn't come out of nowhere.
virushuo (@virushuo) 's Twitter Profile Photo

我们做了一个很有意思的东西。你可以用它来调整R1输出的速度,从而让自己的思考和r1的<think>同步,可以随时暂停修正你觉得R1思考错误的地方,把一些你的思想"植入"R1的思考过程中,最后得到最好的结果。似乎是R1特殊的训练方式,在其他reasoning模型上都很难做到这个。大家可以来玩玩。

Bindu Reddy (@bindureddy) 's Twitter Profile Photo

QwQ-32b Is Indeed The World's Best Open Source Model. We re-ran QwQ with the suggested settings from the Qwen team, and it turns out that it's an AMAZING LLM It's got excellent scores on Livebench AI.

QwQ-32b Is Indeed The World's Best Open Source Model. 

We re-ran QwQ with the suggested settings from the Qwen team, and it turns out that it's an AMAZING LLM

It's got excellent scores on Livebench AI.
Intelligent Internet (@ii_posts) 's Twitter Profile Photo

♊ Introducing II-Researcher: Our open-source AI research agent with strong benchmark performance ♊ 🚀 Key highlights: • New open-source framework for complex, multi-step search with reasoning tasks— a powerful, transparent alternative to proprietary systems • Two methods

♊ Introducing II-Researcher: Our open-source AI research agent with strong benchmark performance ♊

🚀 Key highlights:

• New open-source framework for complex, multi-step search with reasoning tasks— a powerful, transparent alternative to proprietary systems
• Two methods
Intelligent Internet (@ii_posts) 's Twitter Profile Photo

II-Researcher sets a new high on the Google DeepMind FRAMES RAG benchmark with 80% accuracy. Read the in-depth blog post, use the open source code & try it out yourself.

II-Researcher sets a new high on the <a href="/GoogleDeepMind/">Google DeepMind</a> FRAMES RAG benchmark with 80% accuracy.

Read the in-depth blog post, use the open source code &amp; try it out yourself.
Dango233 (@dango233max) 's Twitter Profile Photo

Thank you for choosing SD3.5M as the training base! This is exactly the kind of research we hoped for this Medium (kinda small by today's standard...) sized model!!

Intelligent Internet (@ii_posts) 's Twitter Profile Photo

II-Medical-8B-1706 is our latest state of the art open medical model 💡 Outperforms the latest Google MedGemma 27b model with 70% less parameters 🤏 Quantised GGUF weights, works on <8 Gb RAM 🚀 One more step to the universal health knowledge access that everyone deserves ⚕️

II-Medical-8B-1706 is our latest state of the art open medical model 💡

Outperforms the latest <a href="/Google/">Google</a> MedGemma 27b model with 70% less parameters 🤏

Quantised GGUF weights, works on &lt;8 Gb RAM 🚀

One more step to the universal health knowledge access that everyone deserves ⚕️
Intelligent Internet (@ii_posts) 's Twitter Profile Photo

While building II’s open stack, we put together a Gemini-CLI → MCP+OpenAI a bridge to access the tools + model in our tests. This lets any MCP-savvy agent tap Gemini + its tools via your gemini-cli instance!

While building II’s open stack, we put together a Gemini-CLI → MCP+OpenAI a bridge to access the tools + model in our tests.

This lets any MCP-savvy agent tap Gemini + its tools via your gemini-cli instance!