Original link: https://www.shuizilong.com/house/archives/llama-2/
Where to play Demo
- HuggingChat/Llama-2-70b-chat-hf
- Hugging Face Space 7B | 13B | 70B
- Perplexity 7B/13B
- Replicate 7B | 13B | 70B
- sdk.vercel.ai
- nat.dev
How to play Prompt
<s>[INST]<<SYS>> <</SYS>> [/INST]
<s>[INST]<<SYS>> <</SYS>> [/INST]</s>\ <s>[INST] [/INST]</s>\ <s>[INST] [/INST]
Fine-tuning
Where are there already fine-tuned models?
- https://huggingface.co/spaces/LinkSoul/Chinese-Llama-2-7b
- https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b
how
Other Misc.
This Saturday at 9:00 am Western Time, 12:00 am Eastern Time, let’s talk about how to get LLaMA 2 to exceed the effect of GPT 3.5, if you are interested, let’s discuss together
Topic: LLaMA-2 got a match / surpassed GPT 3.5
Time: Jul 22, 2023 09:00 AM Pacific Time (US and Canada)
https://ed-ac-uk.zoom.us/j/87003419834
Meeting ID: 870 0341 9834
Passcode: abcd1234
ReferencesReference
- LLaMA 2 – Every Resource you need
- Hugging Face, Llama 2 is here – get it on Hugging Face
- Replicate, What happened with Llama 2 in the last 24 hours?
- Replicate, Fine-tune Llama 2 on Replicate
This article is transferred from: https://www.shuizilong.com/house/archives/llama-2/
This site is only for collection, and the copyright belongs to the original author.