Add Llama 3 support

[tonywang16]

[mryab]

Can you put Llama 3-Instruct as a supported model as well? I figure it would be more useful for the chat case

[mryab]

Suggested change

	name="META LLAMA 3 (70B)",
	name="Llama 3 (70B)",

[ELigoP]

When I try running flask app with this config, I get

Apr 30 08:56:56.002 [INFO] Loading tokenizer for meta-llama/Meta-Llama-3-70B
Traceback (most recent call last):
  File "/home/user/.local/bin/flask", line 8, in <module>
    sys.exit(main())
  ...
  File "/home/user/.local/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2032, in from_pretrained
    raise EnvironmentError(
OSError: Can't load tokenizer for 'meta-llama/Meta-Llama-3-70B'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'meta-llama/Meta-Llama-3-70B' is the correct path to a directory containing all relevant files for a LlamaTokenizer tokenizer

I don't know if this is related, but I am also hosting part of GPUs for current public LLama 3 network, so I downloaded at least part of that model. Could that be related?