Comparing Falcon-180B to GPT4
A Quick & Crude Side-By-Side
Falcon-180b dropped on HuggingFace today, and is touted as the “new state-of-the-art for open models”. Most of use won’t be able to host it ourselves, but a nice chatbot demo is already available. Since I have a GPT4 account, thought it would a nice opportunity to compare some side-by-side prompts. According to the release statement:
“Falcon 180B is the best openly released LLM today, outperforming Llama 2 70B and OpenAI’s GPT-3.5 on MMLU, and is on par with Google’s PaLM 2-Large on HellaSwag …. Falcon 180B typically sits somewhere between GPT 3.5 and GPT4 depending on the evaluation benchmark and further finetuning …”
Let’s try it out.
Prompt 1: Coding and S3
How can I set AWS credentials on my laptop so that I don’t have to explicitly pass them around in python code?
GPT4
Falcon180B
