思想与社会2023 · 分享于 Hacker News
GPTQ Accurate Post-Training Quantization for Generative Pre-Trained Transformers
探索《GPTQ Accurate Post-Training Quantization for Generative Pre-Trained Transformers》的原文与 Hacker News 社区讨论,查看来源并加入阅读清单。
从论文,走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问,以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中,并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
Ybehnamoh ·
Apple: Transformer architecture optimized for Apple Silicon
143 赞同55 评论
Ymsoad ·
Llama.cpp 30B runs with only 6GB of RAM now
124 赞同26 评论
YFreddie111 ·
The genie escapes: Stanford copies the ChatGPT AI for less than $600
70 赞同35 评论
Yog_kalu ·
Alpaca- An Instruct Tuned Llama 7B. Responses on par with txt-DaVinci-3. Demo up
53 赞同17 评论
Ypr337h4m ·
LLaMa running at 5 tokens/second on a Pixel 6
39 赞同11 评论
Yrain1 ·
How to run Llama 13B with a 6GB graphics card
16 赞同0 评论
Y0xbadc0de5 ·
LLaMA Text-Generation-Webui
7 赞同1 评论
YMacsHeadroom ·
Nvidia DGX GH200: The First 100 Terabyte GPU Memory System
5 赞同1 评论
YPalmik ·
70B Llama 2 at 35tokens/second on 4090
5 赞同4 评论
Ysimonw ·
Large language models are having their Stable Diffusion moment
4 赞同0 评论
Ymrtksn ·
LLaMA-7B in Pure C++ with full Apple Silicon support
2 赞同1 评论
Ytosh ·
GPTQ Accurate Post-Training Quantization for Generative Pre-Trained Transformers
2 赞同0 评论
Ybelter ·
Do large language models need all those layers?
2 赞同0 评论
Ymrv_asura ·
Matrix Calculus: Calculate derivatives of matrices
1 赞同0 评论
Ysuper256 ·
The tiny corp raised $5.1M
1 赞同0 评论