MARTIN SECKAR
xSakix
AI & ML interests
LLMs
Recent Activity
upvoted an article 6 days ago
Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic reacted to HaotongQin's post with 👍 about 2 years ago
We release an empirical study to showcase "How Good Are Low-bit Quantized hashtag#LLaMA3 🦙 Models" with existing LLM quantization techniques!
In this study, the performance of the low-bit LLaMA3 models (especially LLaMA3-70B) is impressively notable. 🚀 However, the results also exposed significant performance degradation issues faced by existing quantization techniques when dealing with LLaMA3, especially under ultra-low bit-width.
We hope this study can serve as a reference for the LLM quantization community and promote the emergence of stronger LLM quantization methods in the context of LLaMA3's release. More work is on the way...
https://huggingface.co/papers/2404.14047
https://huggingface.co/collections/LLMQ/llama3-quantization-66251258525135aeda16513c liked a Space almost 3 years ago
open-llm-leaderboard/open_llm_leaderboardOrganizations
None yet