Djuunaa's picture

Djuunaa

djuna

·

AI & ML interests

None yet

Recent Activity

reacted to FlameF0X's post with 👍 about 10 hours ago

SnowflakeCore-G1 development update: We're building a 24-layer transformer with 32K context and 1024 embedding dimensions - pretty ambitious! Even running at batch_size=1 with heavy gradient accumulation, we're hitting memory walls at 300GB RAM. Scaling up to ~1TB will take some time, but the architecture is looking promising. Thanks for following along with the journey! 😅

liked a model about 13 hours ago

remyxai/SpaceOm

liked a model about 13 hours ago

prithivMLmods/Camel-Doc-OCR-062825

View all activity

Organizations

liked 2 models about 13 hours ago

remyxai/SpaceOm

Image-Text-to-Text • 4B • Updated about 11 hours ago • 716 • 7

prithivMLmods/Camel-Doc-OCR-062825

Image-Text-to-Text • 8B • Updated 1 day ago • 3

liked a model 4 days ago

OmniGen2/OmniGen2

Any-to-Any • Updated 5 days ago • 20.1k • 237

liked 4 models 5 days ago

Snowflake/Qwen-2.5-coder-Arctic-ExCoT-32B

33B • Updated Apr 2 • 68 • 13

THUDM/SWE-Dev-32B

Text Generation • 33B • Updated 15 days ago • 39 • 24

katanemo/Arch-Agent-32B

Text Generation • 33B • Updated 5 days ago • 127 • • 15

arcee-ai/GLM-4-32B-Base-32K

Text Generation • 33B • Updated 5 days ago • 132 • 29

liked 2 models 6 days ago

cesun/ThinkEdit-deepseek-qwen-32b

Text Generation • 33B • Updated 22 days ago • 25 • 2

BitStarWalkin/S1.1-QwQ-DS

Text Generation • 33B • Updated May 1 • 11 • 2

liked a model 8 days ago

inclusionAI/Ring-lite

17B • Updated 8 days ago • 66 • 9

liked a model 9 days ago

Skywork/Skywork-SWE-32B

Text Generation • 33B • Updated 1 day ago • 820 • • 64

liked a model 10 days ago

arcee-ai/Virtuoso-Large

Text Generation • 73B • Updated 10 days ago • 436 • 26

liked 3 models 12 days ago

YiXin-AILab/YiXin-Distill-Qwen-72B

Text Generation • 73B • Updated May 6 • 48 • 29

BAAI/OpenSeek-Small-v1

2B • Updated 6 days ago • 171 • 14

FreedomIntelligence/Apollo-MoE-7B

Question Answering • 10B • Updated Apr 7 • 89 • 8

liked 2 models 13 days ago

lingshu-medical-mllm/Lingshu-32B

Image-Text-to-Text • 33B • Updated 3 days ago • 1.84k • 38

C10X/Qwen3-Embedding-TurboX.v2

Updated 13 days ago • 205 • 1

liked 3 models 14 days ago

djuna/MN-Chinofun-12B-4.1

Text Generation • 12B • Updated Jan 26 • 67 • 3

neta-art/NetaLumina_Alpha

Updated about 17 hours ago • 27

RUC-AIBOX/STILL-3-TOOL-32B

Text Generation • 33B • Updated Feb 28 • 48 • 5