Carbon-A: Finding genes in known and unknown genomes
• 30
AI & ML interests
Exploring foundation models for DNA and beyond 🧬
Recent Activity
View all activity
Articles
cgeorgiaw
updated a
bucket about 20 hours ago
long sequences compatibility
3
#6 opened 9 days ago
by 
tinyfallen
GenerTeam
updated a
model 3 days ago
loubnabnl
updated a
Space 3 days ago
Contact| brussels airlines telefoonnummer
#2 opened 5 days ago
by 
fdgdfgdfgfdgdfg
Post
4,270
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
loubnabnl
published 2
models 6 days ago
loubnabnl
published a
dataset 6 days ago
lewtun
updated a
collection 7 days ago
Release FineDNA under Apache 2.0 and add a citation
#1 opened 7 days ago
by 
lewtun
loubnabnl
updated a
dataset 7 days ago
lewtun
updated a
dataset 7 days ago
loubnabnl
updated a
model 8 days ago
Point the tech report links at bioRxiv
#2 opened 9 days ago
by lewtun
Use the current repo id in the usage example
#1 opened 9 days ago
by lewtun