fix: correct Llama model name, handle JSON spacing errors, and prevent mode conflicts

[minsing-jin]

What I did

1. Model name error in longwiki_main.py code 66 line

• Model name error. Huggingface lamma 3.1 70B model name is meta-llama/Llama-3.1-70B-Instruct.

2. Fix error caused by incorrect spacing when the model doesn’t follow prompt instructions at longwiki_utils.py check_validity function at 122 line.

• Fix error caused by incorrect spacing when the model doesn’t follow prompt json instructions.

3. Prevent mode selection conflict at precise_wikiqa.py at 269 line.

• If QA_OUTPUT_PATH is specified in condition of do_prompt_generate, we can’t choose between do_prompt_generate, do_inference, or do_eval

[meta-cla]

Hi @minsing-jin!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!

[yjbang]

Thanks for the fixes and suggestions!