Meta 发布开源可商用模型 Llama 2，实际体验效果如何？

Meta刚刚发布了LLaMa 2，这是迄今为止ChatGPT最强大的开源竞争对手

而且，直到你的月活跃用户达到7亿，它的商业使用是免费的。对于开源社区来说，这是一个令人兴奋的新篇章！以下是尝试全新LLaMa 2的11种方法：

1. Perplexity AI Chat https://perplexity.ai/

2. Vercel AI SDK Playground https://sdk.vercel.ai/s/EkDy2iN

3. a16z

游乐场 ： https://llama2.ai/

实时聊天API ： https://replicate.com/a16z-infra/llama13b-v2-chat

4. lmsys Chatbot Arena ：

https://huggingface.co/spaces/lmsys/Chat-and-Battle-with-Open-LLMs

5. HuggingFace Space by ysharma

https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI

6.Your Own Local LLaMa 2 via

https://python.langchain.com/docs/modules/model_io/models/llms/integrations/llamacpp

https://huggingface.co/TheBloke/Llama-2-7B-GGML/blob/main/llama-2-7b.ggmlv3.q4_0.bin

7. Deploy Your Own LLaMa 2 Inference Endpoints

7B: https://ui.endpoints.huggingface.co/new?repository=meta-llama/llama-2-7b-chat-hf

13B: https://ui.endpoints.huggingface.co/new?repository=meta-llama/llama-2-13b-chat-hf

70B: https://ui.endpoints.huggingface.co/new?repository=meta-llama/llama-2-70b-chat-hf

8/ Build from HuggingFace Transformers

https://huggingface.co/blog/llama2#inference

9.Azure用户可以直接在Azure上部署7B、13B 和 70B 参数的 Llama 2 模型。

https://blogs.microsoft.com/blog/2023/07/18/microsoft-and-meta-expand-their-ai-partnership-with-llama-2-on-azure-and-windows/?ocid=FY24_soc_omc_br_tw_Llama

10.AWS

https://aws.amazon.com/cn/blogs/machine-learning/llama-2-foundation-models-from-meta-are-now-available-in-amazon-sagemaker-jumpstart/?advocacy_source=everyonesocial&trk=global_employee_advocacy&sc_channel=sm&es_id=7d2c4387d6

11/另一个可以尝试的地址：https://llama2.skirano.repl.co