Post
34
Please stand by, we will be providing the Nova-1 series with a major architectural and training update. Expect the New Nova-1-Standard release in late October to early November. - Regards, Bc-AI on behalf of Smilyai-Labs
🏗️ Building on HF
Boning Cui
Bc-AI
AI & ML interests
I like LLM's and VLM's.
Recent Activity
updated a model about 7 hours ago
hugging-science/nova-1-exp-checkpoints published a model about 7 hours ago
hugging-science/nova-1-exp-checkpointsOrganizations
posted an update about 8 hours ago
posted an update 12 days ago
Post
143
Hello Everyone! Bc-AI here from Smilyai-labs! Today we have done our latest update for CodVa-1-Small. It is very powerful for coding, and benchmark results will come soon. However, it is NOT good for other tasks, with high hallucination rates. We will perform RLHF and DPO very soon!
posted an update 16 days ago
Post
144
Hello everyone! Today we announce our latest coding model, CodVa-1-Small! It is our most capable model to date for coding, which has completed pretraining and support multi-turn conversation! We will Instruction Tune it very soon! its at: Smilyai-labs/CodVa-1-Small
posted an update 19 days ago
Post
111
I have begun training a new LLM on a Single RTX 6000 Pro Blackwell GPU on MoLab free notebooks. This model is a 10B parameter model designed for coding tasks named CodVa-Large. Please expect a launch in a few months! Meanwhile, our CodVa-Small model is wrapping up pretraining and will launch in the coming weeks. Nova-1-Standard is complete as is and we will launch Large very soon.
replied to Banaxi-Tech's post 20 days ago
@Banaxi-Tech I tested your new model just then and I’d like to say it is possibly the best trained SLM I’ve seen so far. It is very strong in general chat, some simple recipes! The only downside is the math and code is a bit weaker but totally fine in a 50M totally tiny model! Keep up the great work!
replied to their post about 1 month ago
你好！
replied to their post about 1 month ago
in like phase 2 pretraining right now
posted an update about 1 month ago
Post
498
we are going to release our latest NOVEL model next! it's called Nova-1-EXP and will be launched as private preview in the smilyai Laboratories BETA TESTERS organisation.
- 3 replies
posted an update about 1 month ago
Post
159
New Update on Nova-1 series status!!! So, after 3 days of fixing our dataset script, we finally have nova-1-standard in its final phases of instruction tuning hopefully. I genuinely do not know ha-ha. We are also doing a novel model named Nova-1-EXP with 5 novel components in the model, which we will announce when the time comes.
posted an update about 1 month ago
Post
106
Hello everyone! Today we have released a new chat UI for our new LLM! It's at https://nova.smilyai.org and also at: https://huggingface.co/spaces/hugging-science/Nova-1-official-chat
replied to Banaxi-Tech's post about 1 month ago
Impressive! Although, I am curious how powerful the model will be! I have followed so I will see when you release it!
replied to their post about 1 month ago
posted an update about 1 month ago
Post
104
Today, we have released our latest somewhat instruction tuned model! We have also resolved a major issue in our modeling_nova1.py custom code file! We made a zerogpu space to test our model so pleases check it out! its decent at coding, terrible at maths and not good at haiku's. We will continue to improve the model as time passes and the UI will use the latest model by default! https://huggingface.co/spaces/hugging-science/Nova-1-official-chat
- 1 reply
posted an update about 1 month ago
Post
104
Hello everyone! Today we have resolved the transformers incompatibility for Nova-1-Standard-Preview! It is currently loadable, with trust_remote_code as true. If you don't know what Nova-1-Standard is, we suggest you check out our intro video on the model card! https://huggingface.co/Smilyai-labs/Nova-1-Standard-Preview
posted an update about 1 month ago
Post
132
Hello everyone! We are Smilyai-labs, a small team of 4 high school students who love AI and find it very interesting! We are super excited to launch our first preview edition of our Nova-Standard model! Nova-1 is a small family of LLM's which we built from scratch! We designed a custom efficient architecture, featuring MoD layers and much more! We have added RoPE, making it perfect to use YaRN for context extrapolation! From internal tests, we have found that it can support 8K reasonably well and 16K with some performance decreases! Please note, that this is only a Beta version for testing, and we are actively working to fix it! We are only a small group of 4 students, so our progress might be a bit slow! Thank you for your patience! Thank you for checking out our work and a small follow would be appreciated! We are constantly updating, and we will roll out a gradio demo ASAP! Our hugging face org is at: Smilyai-labs . Our model is at: https://huggingface.co/Smilyai-labs/Nova-1-standard-pretrained-preview . The Beta testers org is at: Smilyai-labs-beta-testers .
replied to their post about 1 month ago
Feel free to join the organization! we have posted standard for beta testing already!
posted an update about 2 months ago
Post
227
# 🔥 Nova-1 Beta: Test Our New LLMs!
**Smilyai Labs** is building **Nova-1** — open-source LLMs with novel architectures. Join our beta program!
## 🎯 Available Now:
**Nova-1-Standard (1.2B)** — Phase 2 of pretraining in progress
- PPL 13.5 (beats GPT-2 Large!)
- 48K tok/s on consumer GPUs
- Great for code, reasoning, edge deployment
**Nova-1-Large (3.5B)** — Training live RIGHT NOW
- Current: 30.9 PPL, improving fast, loss at 3.5 right now
- Will finish with ~1.7B tokens today
- Better reasoning & longer context
**Nova-1-XL (10B MoE)** — Coming soon (We dont know yet! haha)
- Final Specs not decided yet
## What Makes Nova Special?
✨ **Mixture of Depths (MoD)** — Routes tokens dynamically, 30% faster
✨ **Grouped Query Attention** — Efficient like LLaMA 2/3
✨ **Phased Training** — Fresh 1B tokens each phase (no overfitting!)
✨ **RoPE** — Context extendable to 8K+
## 🤝 Join Beta Testing:
👉 **[Smilyai-labs-beta-testers]( Smilyai-labs-beta-testers
Get early access, shape the roadmap, and help build transparent open-source AI!
**Smilyai Labs** is building **Nova-1** — open-source LLMs with novel architectures. Join our beta program!
## 🎯 Available Now:
**Nova-1-Standard (1.2B)** — Phase 2 of pretraining in progress
- PPL 13.5 (beats GPT-2 Large!)
- 48K tok/s on consumer GPUs
- Great for code, reasoning, edge deployment
**Nova-1-Large (3.5B)** — Training live RIGHT NOW
- Current: 30.9 PPL, improving fast, loss at 3.5 right now
- Will finish with ~1.7B tokens today
- Better reasoning & longer context
**Nova-1-XL (10B MoE)** — Coming soon (We dont know yet! haha)
- Final Specs not decided yet
## What Makes Nova Special?
✨ **Mixture of Depths (MoD)** — Routes tokens dynamically, 30% faster
✨ **Grouped Query Attention** — Efficient like LLaMA 2/3
✨ **Phased Training** — Fresh 1B tokens each phase (no overfitting!)
✨ **RoPE** — Context extendable to 8K+
## 🤝 Join Beta Testing:
👉 **[Smilyai-labs-beta-testers](
Get early access, shape the roadmap, and help build transparent open-source AI!
- 1 reply
Nice