i will also
🏗️ Building on HF
Boning Cui
Bc-AI
AI & ML interests
I like LLM's and VLM's.
Recent Activity
updated a Space about 3 hours ago
ml-intern-explorers/proxy-space-for updated a Space about 3 hours ago
ml-intern-explorers/inf-end-2 updated a Space about 3 hours ago
ml-intern-explorers/inf-end-1Organizations
replied to ProCreations's post about 3 hours ago
molab.marimo.io
exactly! i can recommend a platform called Molab. It lets to use a free RTX 6000 PRO Blackwell GPU for free. Only caveats are 12 hour sessions so add some huggingface session checkpointing.
This has to be engagement bait/ragebait right?
I’m pretty sure it is
replied to Banaxi-Tech's post 3 days ago
This model is extremely capable for its size. Good job
replied to ProCreations's post 5 days ago
nice!
nice!
reacted to darkc0de's post with 👀❤️🤯 6 days ago
Post
14247
1440GB of VRAM is incredibly satisfying 😁
- 18 replies
posted an update 8 days ago
Post
114
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
posted an update 20 days ago
Post
173
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 24 days ago
Post
150
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 26 days ago
Post
113
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 28 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
500
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
161
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 2 months ago
Post
108
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