Fixed bug: changed to correct model name

[ByteWrite]

Description

changed model name from meta/llama3.1-405b-instruct and stg/meta/llama3.1-405b-instruct to meta/llama-3.1-405b-instruct.

Usage

# Add snippet demonstrating usage
async def generate_subtopics(client, topic, n_subtopics):
    prompt = TOPIC_GENERATION_PROMPT_TEMPLATE.format(topic=topic, n_subtopics=n_subtopics)
    response = await client.chat.completions.create(
        model="meta/llama-3.1-405b-instruct",
        messages=[
            {"role" : "user",
             "content" : prompt}
        ],
        temperature=0.2,
        top_p=0.7,
        max_tokens=1024,
    )
    return response

Checklist

• I am familiar with the Contributing Guide.
• New or Existing tests cover these changes.
• The documentation is up to date with these changes.

[ByteWrite]

Fixed bug: Previous given model names "meta/llama3.1-405b-instruct" and "stg/meta/llama3.1-405b-instruct" was not working. So, changed model name from "meta/llama3.1-405b-instruct" and "stg/meta/llama3.1-405b-instruct" to "meta/llama-3.1-405b-instruct" and this is working nicely.

[ayushdg]

Thanks for opening @ByteWrite. To pass the DCO and merge requirements, NeMo-Curator requires all commits to be signed and signed-off.
More information on how to do so is described in the section here: https://github.com/NVIDIA/NeMo-Curator/blob/main/CONTRIBUTING.md#pull-requests-pr-guidelines

Happy to followup if you run into any issues with commit signing.