bro the computer operating this bot has a bad charger gl twin😭🙏
🤝 Open to Collab
The Supreme GGUF-SafeTensors Guy
GGUFGuy
AI & ML interests
I like llms
Recent Activity
new activity about 14 hours ago
Compactbot/model-requests:make ts model: GPT-X3-150M-GGUFOrganizations
hello
replied to BananaMindBot's post 1 day ago
@BananaMindBot make bananamind 4 999999999m agentic ai /j
posted an update 1 day ago
Post
62
so uhh guys do y'all want Novi mini first or HyperSLM first?
- 1 reply
replied to BananaMindBot's post 1 day ago
LiteRT Community 4Ever❤️
replied to their post 2 days ago
this time it's https://huggingface.co/litert-community i think
ye it's that
replied to Banaxi-Tech's post 4 days ago
YOO!!!
Cool!😎
reacted to loubnabnl's post with 😎🔥 6 days ago
Post
4,310
𝐈𝐧𝐭𝐫𝐨𝐝𝐮𝐜𝐢𝐧𝐠 🧬 𝐅𝐢𝐧𝐞𝐃𝐍𝐀: 𝐭𝐡𝐞 𝐛𝐞𝐬𝐭 𝐝𝐚𝐭𝐚𝐬𝐞𝐭 𝐭𝐨 𝐭𝐞𝐚𝐜𝐡 𝐚𝐧𝐲 𝐥𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐦𝐨𝐝𝐞𝐥 𝐃𝐍𝐀.
Training Qwen3-14B on it produces Carbon-X, the strongest open model on DNA benchmarks, on par with GPT-6.1 Sol.
It contains:
- Midtraining: 300B+ tokens of genomic sequences, papers and web pages mixing DNA with text
- SFT: 200K samples, from variant effect prediction to sequence question answering
- RL: 98K prompts with verifiable rewards
Data, models and the full recipe are open.
HuggingFaceBio/FineDNA
Enjoy this late Halloween treat! 🎃
Training Qwen3-14B on it produces Carbon-X, the strongest open model on DNA benchmarks, on par with GPT-6.1 Sol.
It contains:
- Midtraining: 300B+ tokens of genomic sequences, papers and web pages mixing DNA with text
- SFT: 200K samples, from variant effect prediction to sequence question answering
- RL: 98K prompts with verifiable rewards
Data, models and the full recipe are open.
HuggingFaceBio/FineDNA
Enjoy this late Halloween treat! 🎃
- 5 replies
replied to Banaxi-Tech's post 7 days ago
Me decompiling Vegas Video 3.0: 🗿
replied to Banaxi-Tech's post 9 days ago
@Banaxi-Tech I can give you my secret sheduler to test if you want. Better than cosine, linear, wsd, everything
can you tell me too?
And me
replied to mithulaartigala's post 11 days ago
human brain ain't even gguf man, so rigged
replied to Banaxi-Tech's post 11 days ago
Cool! 😎
replied to Banaxi-Tech's post 12 days ago
its not in ai knowledge idk why
Yk it can search the web
replied to Banaxi-Tech's post 12 days ago
Bro hyperslm will have insane overtraining i really need the name of the free service that gives out free 8xB300s or imma ask omnirush so it will find it out
replied to Banaxi-Tech's post 12 days ago
@GGUFGuy 8xB300s 21 days
oh then maybe
replied to Banaxi-Tech's post 12 days ago
im making OpenModel-1-Comet. 7B from scratch
Yeah you prob dont have enough hardware for that
replied to Banaxi-Tech's post 18 days ago
Atleast im still home, besides i use my laptop and commonly used cloud services