Hugging Face's logo
Sthenno's picture
20 4 315

Sthenno

sthenno
win10's profile picture Zeldazackman's profile picture wanlige's profile picture
·
https://github.com/neoheartbeats

AI & ML interests

To contact me: [email protected]

Recent Activity

liked a model 3 days ago
shuttleai/shuttle-3.5
reacted to sometimesanotion's post with 👀 5 days ago
The capabilities of the new Qwen 3 models are fascinating, and I am watching that space! My experience, however, is that context management is vastly more important with them. If you use a client with a typical session log with rolling compression, a Qwen 3 model will start to generate the same messages over and over. I don't think that detracts from them. They're optimized for a more advanced MCP environment. I honestly think the 8B is optimal for home use, given proper RAG/CAG. In typical session chats, Lamarck and Chocolatine are still my daily drives. I worked hard to give Lamarck v0.7 a sprinkling of CoT from both DRT and Deepseek R1. While those models got surpassed on the leaderboards, in practice, I still really enjoy their output. My projects are focusing on application and context management, because that's where the payoff in improved quality is right now. But should there be a mix of finetunes to make just the right mix of - my recipes are standing by.
reacted to sometimesanotion's post with ❤️ 5 days ago
The capabilities of the new Qwen 3 models are fascinating, and I am watching that space! My experience, however, is that context management is vastly more important with them. If you use a client with a typical session log with rolling compression, a Qwen 3 model will start to generate the same messages over and over. I don't think that detracts from them. They're optimized for a more advanced MCP environment. I honestly think the 8B is optimal for home use, given proper RAG/CAG. In typical session chats, Lamarck and Chocolatine are still my daily drives. I worked hard to give Lamarck v0.7 a sprinkling of CoT from both DRT and Deepseek R1. While those models got surpassed on the leaderboards, in practice, I still really enjoy their output. My projects are focusing on application and context management, because that's where the payoff in improved quality is right now. But should there be a mix of finetunes to make just the right mix of - my recipes are standing by.
View all activity

Organizations

MLX Community's profile picture Hugging Face Discord Community's profile picture sthenno-com's profile picture

Collections 2

datasets 0

None public yet