Hm, did you use the pretrained weights from Meta? Does the model work fine if you don't do any training and don't pass any image tokens?
OPEN SOURCE
-
Ego Toll: Credibility Loss Resistance in Improvement Steps
By
–
What is the "ego toll"? It's when people push back against even a small step toward improvement, if that step involves a perceived loss of credibility, authority, or control https://
bit.ly/3EWiSgr #opensource #productdev -
OlympicCoder Beats Claude 3.7 in Competitive Programming
By
–
Wow, we've kept pushing our Open-R1 project, an open initiative to replicate and extend the techniques behind DeepSeek-R1 And even we were mind-blown by the results we got with this latest model we're releasing: OlympicCoder It's beating Claude 3.7 on (competitive)
-
Llama.cpp Image-Compatible Playground Guide Released
By
–
BTW Son's image-compatible playground is super cool Guide on how to run it: https://
github.com/ggml-org/llama
.cpp/discussions/12348
… -
Gemma 3 27B now on AI Studio
By
–
Gemma 3 27B is also now available on AI Studio 👀 https://t.co/Ri94aTOfxE pic.twitter.com/39LqzE5LKq
— 🚨 AI News | TestingCatalog (@testingcatalog) 12 mars 2025Gemma 3 27B is also now available on AI Studio
-
Google Releases Gemma 3 in Four Sizes
By
–
Google released Gemma 3, SOTA open model in 4 different sizes: 1B, 4B, 12B, 27B https://t.co/UFFPsYE7pg pic.twitter.com/cR0uT8NDsc
— 🚨 AI News | TestingCatalog (@testingcatalog) 12 mars 2025Google released Gemma 3, SOTA open model in 4 different sizes: 1B, 4B, 12B, 27B
-
Manus Partners with Alibaba Qwen for Chinese Autonomous Agent
By
–
The team behind Manus partnered with Alibaba's Qwen to develop a Chinese version of its autonomous agent
— Rowan Cheung (@rowancheung) 12 mars 2025
The collaboration will integrate Manus with Qwen's open-source models and computing infra
This comes just after Manus went viral last week!pic.twitter.com/encoTIamO3The team behind Manus partnered with Alibaba's Qwen to develop a Chinese version of its autonomous agent The collaboration will integrate Manus with Qwen's open-source models and computing infra This comes just after Manus went viral last week!
-
Reka Open-Sources Flash 3: 21B Reasoning Model for On-Device AI
By
–
Reka open-sourced Flash 3, a 21B parameter reasoning model
— Rowan Cheung (@rowancheung) 12 mars 2025
—Matches o1-mini on benchmarks
—32k context length
—Ideal for on-device deployment
—Finetuned on synthetic and public datasets
—Powers Nexus, Reka's platform for creating and managing AI agentspic.twitter.com/FTzKc8NtM8Reka open-sourced Flash 3, a 21B parameter reasoning model —Matches o1-mini on benchmarks
—32k context length
—Ideal for on-device deployment
—Finetuned on synthetic and public datasets
—Powers Nexus, Reka's platform for creating and managing AI agents -
OpenAI Launches DIY Custom AI Agent Building Tools and SDK
By
–
OpenAI released new DIY tools for building custom AI agents, including:
— Rowan Cheung (@rowancheung) 12 mars 2025
A CUA model-powered Responses API with tools for web browsing, computer use, and file management
An open-source Agents SDK to orchestrate single and multi-agent systemspic.twitter.com/70QcVRL3EFOpenAI released new DIY tools for building custom AI agents, including: A CUA model-powered Responses API with tools for web browsing, computer use, and file management An open-source Agents SDK to orchestrate single and multi-agent systems
-
RekaAI joins open-source AI movement
By
–
Welcome to the open-source side of History (the right side?) @RekaAILabs ! Super exciting