wmertens/smollm-ternary
Updated
Wout Mertens
wmertens
·
AI & ML interests
None yet
Recent Activity
published a model about 7 hours ago
wmertens/smollm-ternary updated a model 9 days ago
wmertens/bitlooplm-small liked a model 9 days ago
ByteDance/Ouro-2.6B-ThinkingOrganizations
published a
model about 7 hours ago
updated a
model 9 days ago
liked a
model 9 days ago
reacted to Benedictat's post with 👍 13 days ago
Post
3566
Built a WeChat Mini Program in 20 minutes flat with Hy3 Preview + WorkBuddy…
and I didn’t type a single line of code. Not even a semicolon.
This Coding Agent is on steroids. Its comprehension in long back-and-forths is night and day better, and that 256K context window swallows the entire project structure whole.
Tell it what you want, and it actually gets the full picture no confused blank stares from the AI.
And we’re not messing around with dinky little code snippets here. It spits out a fully functional project
app.json, every page’s wxml/wxss/js/json, even Mock data pre-packed. Import it into WeChat Dev Tools and it runs on the first try
Only one tiny visual nitpick, zero logic bugs. Point out the flaw, and it fixes it instantly no new bugs, no passive-aggressive code breaks, no headaches
The entire vibe Tell it your idea → Get a complete working project → Mention a tiny flaw → AI polishes it.
No coding, no endless edits, no soul-crushing debugging that makes you want to throw your laptop. Absolute game-changer
and I didn’t type a single line of code. Not even a semicolon.
This Coding Agent is on steroids. Its comprehension in long back-and-forths is night and day better, and that 256K context window swallows the entire project structure whole.
Tell it what you want, and it actually gets the full picture no confused blank stares from the AI.
And we’re not messing around with dinky little code snippets here. It spits out a fully functional project
app.json, every page’s wxml/wxss/js/json, even Mock data pre-packed. Import it into WeChat Dev Tools and it runs on the first try
Only one tiny visual nitpick, zero logic bugs. Point out the flaw, and it fixes it instantly no new bugs, no passive-aggressive code breaks, no headaches
The entire vibe Tell it your idea → Get a complete working project → Mention a tiny flaw → AI polishes it.
No coding, no endless edits, no soul-crushing debugging that makes you want to throw your laptop. Absolute game-changer
reacted to SeanLee97's post with 👍 13 days ago
Post
8134
Our lab recently released a paper where we introduce ShadowPEFT, a new Parameter-Efficient Fine-Tuning (PEFT) paradigm tailored for edge computing scenarios.
Unlike traditional approaches such as LoRA and its variants, which inject trainable parameters directly into the weights of Transformer, requiring tight coupling with the backbone.
ShadowPEFT instead enhances the frozen large base model by adding a lightweight, centralized, pretrainable, and detachable Shadow network.
This shadow network operates in parallel with the base model, delivering learned corrections to each decoder layer. Because the shadow module is architecturally decoupled from the backbone, it can be independently trained, stored, and deployed, benefiting edge computing scenarios and edge-cloud collaboration computing.
- HF Paper: ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning (2604.19254)
- GitHub: https://github.com/ShadowLLM/shadow-peft
- HF Collection: https://huggingface.co/collections/shadow-llm/shadow-peft-models
Unlike traditional approaches such as LoRA and its variants, which inject trainable parameters directly into the weights of Transformer, requiring tight coupling with the backbone.
ShadowPEFT instead enhances the frozen large base model by adding a lightweight, centralized, pretrainable, and detachable Shadow network.
This shadow network operates in parallel with the base model, delivering learned corrections to each decoder layer. Because the shadow module is architecturally decoupled from the backbone, it can be independently trained, stored, and deployed, benefiting edge computing scenarios and edge-cloud collaboration computing.
- HF Paper: ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning (2604.19254)
- GitHub: https://github.com/ShadowLLM/shadow-peft
- HF Collection: https://huggingface.co/collections/shadow-llm/shadow-peft-models
- 7 replies
upvoted 2
articles 13 days ago
Article
What superpower does Kimi-K2.5 bring to the table?
•
5
Article
Hy3 preview: A Rebuilt Hunyuan, a 21B-Active MoE, and a New Reasoning Receipe
•
5
replied to imnotkitty's post 13 days ago
Awesome! Why is it considered a preview?
reacted to imnotkitty's post with 🔥 13 days ago
Post
3954
tencent/Hy3-preview is out: an open-weights MoE reasoning model.
✅ 295B total / 21B active / 256K context
✅ Fused fast-and-slow thinking in a single model
✅ First model trained on Hunyuan's rebuilt pretraining + RL infra (Feb → Apr)
Benchmarks:
👉 SWE-Bench Verified, Terminal-Bench 2.0, BrowseComp, WideSearch — competitive results, particularly strong on agentic tool use
👉 Top score on Tsinghua's 2026 Spring math PhD qualifying exam
👉 Strong context-learning and instruction-following on Tencent's CL-bench / CL-bench-Life
More details can be found in my article: https://huggingface.co/blog/imnotkitty/hy3-preview
✅ 295B total / 21B active / 256K context
✅ Fused fast-and-slow thinking in a single model
✅ First model trained on Hunyuan's rebuilt pretraining + RL infra (Feb → Apr)
Benchmarks:
👉 SWE-Bench Verified, Terminal-Bench 2.0, BrowseComp, WideSearch — competitive results, particularly strong on agentic tool use
👉 Top score on Tsinghua's 2026 Spring math PhD qualifying exam
👉 Strong context-learning and instruction-following on Tencent's CL-bench / CL-bench-Life
More details can be found in my article: https://huggingface.co/blog/imnotkitty/hy3-preview
- 2 replies
updated a
Space 13 days ago
published a
model 15 days ago
updated a
Space 15 days ago
upvoted a collection 10 months ago
upvoted an article 11 months ago
Article
All LLMs Will Be Sparse BitNet Hybrids
•
16