Fix duplicate model_names for llama2-70b benchmarks

[bvandermoon]

Description

There are several benchmarks named llama2_70b_4096. I tried to run this benchmark but was getting a different config then expected. A different llama2 benchmark with the same name was getting pulled instead of mine. This PR changes the other benchmark names to reduce duplicates.

Tests

• Ran the benchmarks with the updated names and the workloads kicked off properly (although they fail for other reasons)

Checklist

Before submitting this PR, please make sure (put X in square brackets):

• I have performed a self-review of my code.
• I have necessary comments in my code, particularly in hard-to-understand areas.
• I have run end-to-end tests tests and provided workload links above if applicable.
• I have made or will make corresponding changes to the doc if needed.