ไฝ ๅฅฝ๏ผ
๐๏ธ Building on HF
Boning Cui
Bc-AI
AI & ML interests
I like LLM's and VLM's.
Recent Activity
liked a model about 15 hours ago
empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUFOrganizations
replied to their post about 15 hours ago
replied to their post 1 day ago
in like phase 2 pretraining right now
posted an update 1 day ago
Post
70
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 8 days ago
Post
129
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 9 days ago
Post
89
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 11 days 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 11 days ago
posted an update 11 days ago
Post
93
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 13 days ago
Post
93
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 14 days ago
Post
121
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 15 days ago
Feel free to join the organization! we have posted standard for beta testing already!
posted an update 17 days ago
Post
221
# ๐ฅ Nova-1 Beta: Test Our New LLMs!
**Smilyai Labs** is building **Nova-1** โ open-source LLMs with novel architectures. Join our beta program!
## ๐ฏ Available Now:
**Nova-1-Standard (1.2B)** โ 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)** โ 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)** โ Coming soon (We dont know yet! haha)
- Final Specs not decided yet
## What Makes Nova Special?
โจ **Mixture of Depths (MoD)** โ Routes tokens dynamically, 30% faster
โจ **Grouped Query Attention** โ Efficient like LLaMA 2/3
โจ **Phased Training** โ Fresh 1B tokens each phase (no overfitting!)
โจ **RoPE** โ Context extendable to 8K+
## ๐ค Join Beta Testing:
๐ **[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** โ open-source LLMs with novel architectures. Join our beta program!
## ๐ฏ Available Now:
**Nova-1-Standard (1.2B)** โ 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)** โ 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)** โ Coming soon (We dont know yet! haha)
- Final Specs not decided yet
## What Makes Nova Special?
โจ **Mixture of Depths (MoD)** โ Routes tokens dynamically, 30% faster
โจ **Grouped Query Attention** โ Efficient like LLaMA 2/3
โจ **Phased Training** โ Fresh 1B tokens each phase (no overfitting!)
โจ **RoPE** โ Context extendable to 8K+
## ๐ค Join Beta Testing:
๐ **[Smilyai-labs-beta-testers](
Get early access, shape the roadmap, and help build transparent open-source AI!
- 1 reply
Nice