Evaluate yi-coder models

[haesleinhuepf]

This PR contains:

• a new test-case for the benchmark
  • I hereby confirm that NO LLM-based technology (such as github copilot) was used while writing this benchmark
• new dependencies in requirements.txt
  • The environment.yml file was updated using the command conda env export > environment.yml
• new generator-functions allowing to sample from other LLMs
• new samples (sample_....jsonl files)
• new benchmarking results (..._results.jsonl files)
• documentation update
• bug fixes

Related github issue (if relevant): closes #0

Short description:

• I was benchmarking two models: yi-coder 1.5B and 9B

How do you think will this influence the benchmark results?

• The two models are not super excitingly good.
  

Why do you think it makes sense to merge this PR?

• I saw the model in social media and had the impression it might be good. Now that I see the benchmark results, I'm not sure if its relevant. However, als negative results are results. Hence, we should merge this...