Running on Zero MCP Featured 110 FLUX.2 Klein 9B KV ๐จ 110 Generate or edit images from text and optional photos
view post Post 5357 Surya-1.1T: Scaling Beyond Human-Level Reasoning via 146 Trillion Token Pre-trainingAuthor: SKT AI LABSAffiliation: SKT AI Labs / Project SuryaModel Architecture: Optimized Dense TransformerParameters: 1.1 TrillionTraining Tokens: 146 TrillionWanna collaborate us Friends let's Start Journey we have Collected 146 trillon tokens and done pre training but we need to made more powerfullWhitepaper - https://github.com/SHRIJANAGAIN/PROFF See translation 49 replies ยท ๐ฅ 15 15 ๐ 9 9 ๐ 8 8 ๐ค 7 7 โ 7 7 ๐ 6 6 โค๏ธ 6 6 ๐ 5 5 ๐ง 5 5 ๐ค 5 5 ๐คฏ 3 3 + Reply
view post Post 3812 Can small models program?Although even if they are reasoning AIs, small AIs cannot create extensive and high-quality code, at least that's what is commonly thought.We present OrionLLM/NanoCoder-0.6b, an AI with just 600 million parameters based on qwen3-0.6b and trained with the dataset nvidia/OpenCodeReasoning.While not good at complex code, we observed a significant improvement in code generation (especially in Python code), demonstrating that, when trained correctly, small AIs can, in fact, program. See translation 2 replies ยท ๐ค 9 9 ๐ 1 1 ๐ฅ 1 1 + Reply