AI & ML interests

None defined yet.

Recent Activity

Articles

loubnabnl 
posted an update 3 days ago
view post
Post
4,120
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! 🎃
  • 4 replies
·
albertvillanova 
posted an update 6 days ago
view post
Post
184
Day-0 Mistral Large 4 support in TRL 🚀

- LoRA SFT of the 1T-A52B model on one 8xB300 node, on top of the FP8 checkpoint
- Experts split 8 ways with expert parallelism, everything else sharded with FSDP, all set at load time
- Assistant-only loss out of the box with its training chat template
- ~32.7k tokens per step in ~8 s

Script + Slurm launcher 👇
https://github.com/huggingface/trl/tree/main/examples/sft_mistral_large_4
https://huggingface.co/posts/sergiopaniego/408182860646834
anton-l 
in bigcode/the-stack 3 months ago

ccc

#58 opened 11 months ago by
zhuyunqiang111

bigcode/the-stack

#57 opened 11 months ago by
zhuyunqiang111

the-stack

#56 opened 11 months ago by
zhuyunqiang111

Project

#55 opened 11 months ago by
needmoney4porsche

123

#32 opened over 3 years ago by
gopherrrr

Update README.md

#46 opened almost 2 years ago by
Tjasika

Upload 37 files

#48 opened almost 2 years ago by
crystalai

unsafe so delete

#50 opened over 1 year ago by
jayan12k

hhjgj

👍 1
#54 opened about 1 year ago by
Anil1908

Delate data/D

#11 opened over 1 year ago by
MIN12352
anton-l 
in bigcode/the-stack 3 months ago

Apply opt-out removals

#64 opened 3 months ago by
anton-l

LLMQuantResearch

#63 opened 4 months ago by
suvodeep1007