6 3

Crispin Almodovar

calmodovar23

AI & ML interests

None yet

Recent Activity

updated a dataset about 1 month ago

corto-ai/nsw-caselaw-qa-embed

liked a model about 2 months ago

fal/AuraSR-v2

View all activity

Organizations

calmodovar23's activity

updated a dataset about 1 month ago

corto-ai/nsw-caselaw-qa-embed

Viewer • Updated Dec 6, 2024 • 30.4M • 29

liked a model about 2 months ago

fal/AuraSR-v2

Image-to-Image • Updated Aug 7, 2024 • 1.86k • 241

liked a Space 4 months ago

Running

588

🌖

Qwen2-VL-72B

reacted to m-ric's post with 🔥 4 months ago

Post

2176

𝗔𝗿𝗰𝗲𝗲 𝗿𝗲𝗹𝗲𝗮𝘀𝗲𝘀 𝗦𝘂𝗽𝗲𝗿𝗡𝗼𝘃𝗮, 𝗯𝗲𝘁𝘁𝗲𝗿 𝗳𝗶𝗻𝗲-𝘁𝘂𝗻𝗲 𝗼𝗳 𝗟𝗹𝗮𝗺𝗮-𝟯.𝟭-𝟳𝟬𝗕!

2️⃣ versions: 70B and 8B
🧠 Trained by distilling logits from Llama-3.1-405B
🐥 Used a clever compression method to reduce dataset weight from 2.9 Petabytes down to 50GB (may share it in a paper)
⚙️ Not all benchmarks are improved: GPQA and MUSR go down a slight bit
🤗 8B weights are available on HF (not the 70B)

Read their blog post 👉 https://blog.arcee.ai/arcee-supernova-training-pipeline-and-model-composition/
Model weights (8B) 👉 arcee-ai/Llama-3.1-SuperNova-Lite