@harnecient
Account based inUnited States
About this account
- Account based in
- United States
- Connected via
- Web
Account-level information from X, not a live location or the device used for a specific post.
Get (a lot) more out of your AI tools , faster. Who wouldn't want that? Consumer and B2B solutions.
SF -
Joined January 2026
- Tweets513
- Following629
- Followers29
- Likes1.3K
Jev模型热后，马上出来了开源版本的Jev，都是可以在本地进行训练和推理的，可以先体验。
一个基于 Qwen2.5-0.5B 构建的小型 Jev 型模型，可以在 MacBook 上进行训练和运行。（接了一个LoRa微调qwen2.5）
github.com/jaredpalmer/kev
在家使用3090显卡，基于开放模型进行语义if判断。独立完成；与Jev或TypeSafe无任何关联。
github.com/TheoLeeCJ/SemIf
Harnecient retweeted
Here you go github.com/narphorium/nl-log…
Harnecient retweeted
The magic isn’t in being the “first” to an idea but the first to make it “just work.”
That is the bitterest lesson for folks in this field.
Harnecient retweeted
github.com/githubnext/localj…
Not everyone on the team has access to Jev yet. Spent a morning cobbling together a poor man's Jev on top of omlx for local use. Benchmarked and eval'ed a variety of models including diffusiongemma and a variety of autoregressive models (Qwen MoE, Gemma 4 MoE, and Gemma 4 e4b/e2b.) Benchmark report is in the repo.
This is 100% promptcoding but hey the evals look okay, speeds are pretty good on local machine (m5 max 64gb), and the LocalJev server exposes an API that can be used with the normal Jev API wrapper libraries.
