Splat's picture

In a Training Loop 🔄

Splat

itsnotsplat

·

splat1745

AI & ML interests

None yet

Recent Activity

updated a collection 9 days ago

liked a dataset 16 days ago

angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k

liked a model 16 days ago

deepseek-ai/DeepSeek-V4-Pro

View all activity

Organizations

upvoted a collection about 1 month ago

Unsloth Dynamic 2.0 Quants

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 96 items • Updated 3 days ago • 626

upvoted 2 collections 3 months ago

Pretraining

This is general pretraining data for training a model from scratch. Around ~2.1 trillion tokens. • 9 items • Updated Mar 29 • 1

Post-training

This is data used after pre-training. Contains around ~2.8 billion tokens. • 7 items • Updated 9 days ago • 1

upvoted a collection 10 months ago

Meta's Llama 3.2 language models & evals

14 items • Updated Dec 13, 2024 • 445