Fix llama3 urls + chat completion termination + nightlies in readme

[mreso]

What does this PR do?

This PR fix:

• Identifiers for llama3 in tests
• Correct termination condition in chat completion example
• Remove nightlies installation in readme

Fixes # (issue)

Feature/Issue validation/testing

Please describe the tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced.
Please also list any relevant details for your test configuration.

• Test A
  Logs for Test A

• Test B
  Logs for Test B

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a Github issue? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

Thanks for contributing 🎉!

[jeffxtang]

message the model => message, the model

[jeffxtang]

generation we => generation, we

[HamidShojanazeri]

@mreso is it like two the two EOS terminators should be used to stop generation early? wonder if that. matches our description here or we need a bit of lingo?

[subramen]

Is the eos_token_id arg in model.generate specifying the stop sequence for generation?

I think some lingo around understanding the difference between eot_id and end_of_text usage would be helpful

[mreso]

Thanks for the comments! Yes, the eos_token_id is the one thats checked in the stopping criteria and usually thats set to <|end_of_text|>. But for dialog kind of prompt the model is trained to use <|eot_id|> (probably to distinguish it from the more final end of sequence). Thats why we need to replace the eos_token_id against the latter id. Otherwise generate rambles on like in this example:

Model output:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>

Always answer with emojis<|eot_id|><|start_header_id|>user<|end_header_id|>

How to go from Beijing to NY?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

🛫️🚀🛬<|eot_id|><|start_header_id|>assistant<|end_header_id|>

🏨🛬🇨🇳                                                                                                                                                                                                                                 🕰️ 12+hours o
💺Business Class
[...]

The model learned that after an <|eot_id|> comes another header so its adds <|start_header_id|>assistant<|end_header_id|> and then comes another response. (The header is usually appended by the chat template, not the model)
If we exchange the eos_token_id in generate it stops after the model emits the first <|eot_id|>:

Model output:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>

Always answer with emojis<|eot_id|><|start_header_id|>user<|end_header_id|>

How to go from Beijing to NY?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

✈️ 🗼️🛬<|eot_id|>

Will rework the text accordingly before merigng.

[HamidShojanazeri]

So this should have been addressed in this PR which has been merged, https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/discussions/4/files

[HamidShojanazeri]

thanks @mreso just a minor comment if we need to tune the language a bit? if not I am fine with it.

[HamidShojanazeri]

@mreso is it like two the two EOS terminators should be used to stop generation early? wonder if that. matches our description here or we need a bit of lingo?

[subramen]

LGTM! only added a minor suggestion to include detail on how developers should use eos_tokens

[HamidShojanazeri]

just left minor comments we discussed offline, otherwise, LGTM thanks!

[Karliz24]