dev7halo's picture

dev7halo

dev7halo

·

HaloKim

AI & ML interests

None yet

Recent Activity

liked a model about 11 hours ago

cccczshao/CALM-L

liked a dataset 15 days ago

LGAI-EXAONE/Ko-LongRAG

reacted to gokaygokay's post with 🔥 15 days ago

FlashPack: Lightning-Fast Model Loading for PyTorch https://github.com/fal-ai/flashpack FlashPack — a new, high-throughput file format and loading mechanism for PyTorch that makes model checkpoint I/O blazingly fast, even on systems without access to GPU Direct Storage (GDS). With FlashPack, loading any model can be 3–6× faster than with the current state-of-the-art methods like accelerate or the standard load_state_dict() and to() flow — all wrapped in a lightweight, pure-Python package that works anywhere.

View all activity

Organizations

New activity in trillionlabs/Tri-70B-preview-SFT about 1 month ago

chat template bug

#2 opened about 1 month ago by

New activity in skt/A.X-4.0 4 months ago

ax vllm mcp template, jinja

#1 opened 4 months ago by

New activity in kakaocorp/kanana-1.5-8b-instruct-2505 6 months ago

kanana vllm mcp template, jinja

#1 opened 6 months ago by

New activity in naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B 7 months ago

Thanks for sharing !

#2 opened 7 months ago by

New activity in meta-llama/Meta-Llama-Guard-2-8B over 1 year ago

Why do I get results without filling out the prompt?

#11 opened over 1 year ago by