llama 3.1效果有多好，全网铺天盖地的推文，已经无需多言了。
如果是简单试用，可以在huggingface chat上试用https://huggingface.co/chat/models/meta-llama/Meta-Llama-3.1-405B-Instruct-FP8
cpu本地跑，可以试试gguf量化，可以得到1.67 token/s的输出，10 token/s的输入，很慢但是不是不可用~
首先下载gguf权重：https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf
权重这么大，怎么快速下载呢？试用Aria2并行下载。
linux: apt install -y aria2 ；Mac: brew install aria2
下载权重：
aria2c -x 16 -s 16 -k 1M -o meta-405b-inst-cpu-optimized-q4048-00001-of-00006.gguf https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf/resolve/main/meta-405b-inst-cpu-optimized-q4048-00001-of-00006.gguf
aria2c -x 16 -s 16 -k 1M -o meta-405b-inst-cpu-optimized-q4048-00002-of-00006.gguf https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf/resolve/main/meta-405b-inst-cpu-optimized-q4048-00002-of-00006.gguf
aria2c -x 16 -s 16 -k 1M -o meta-405b-inst-cpu-optimized-q4048-00003-of-00006.gguf https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf/resolve/main/meta-405b-inst-cpu-optimized-q4048-00003-of-00006.gguf
aria2c -x 16 -s 16 -k 1M -o meta-405b-inst-cpu-optimized-q4048-00004-of-00006.gguf https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf/resolve/main/meta-405b-inst-cpu-optimized-q4048-00004-of-00006.gguf
aria2c -x 16 -s 16 -k 1M -o meta-405b-inst-cpu-optimized-q4048-00005-of-00006.gguf https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf/resolve/main/meta-405b-inst-cpu-optimized-q4048-00005-of-00006.gguf
aria2c -x 16 -s 16 -k 1M -o meta-405b-inst-cpu-optimized-q4048-00006-of-00006.gguf https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf/resolve/main/meta-405b-inst-cpu-optimized-q4048-00006-of-00006.gguf
然后就可以试用llama.cpp跑起来了
./llama-cli -t 32 --temp 0.4 -fa -m ~/meow/meta-405b-inst-cpu-optimized-q4048-00001-of-00006.gguf -b 512 -c 9000 -p "Adopt the persona of a NASA JPL mathmatician and firendly helpful programmer." -cnv -co -i
占用个246GB。
PS：给公众号添加【星标⭐️】不迷路！您的点赞、在看、关注 是我坚持的最大动力！
欢迎多多关注公众号「NLP前沿」，加入交流群，交个朋友吧，一起学习，一起进步！
最新文章推荐阅读