llama-int8 VS test

If anyone is interested in running this at home, please follow the llama-int8 project [1]. LLM.int8() is a recent development allowing LLMs to run in half the memory without loss of performance [2]. Note that at the end of [2]'s abstract, the authors state "This result makes such models much more accessible, for example making it possible to use OPT-175B/BLOOM on a single server with consumer GPUs. We open-source our software." I'm very thankful we have researchers like this further democratizing access to this data and prying it out of the hands of the gatekeepers who wish to monetize it.

[1] https://github.com/tloen/llama-int8

[2] https://arxiv.org/abs/2208.07339

To add a bit more context, the code other people linked (https://github.com/tloen/llama-int8) assumes single GPU. So if you want to run it on 2x3090, you'll need to modify it a bit:

Sources [1] MMLU Benchmark (Multi-task Language Understanding) | Papers With Code https://paperswithcode.com/sota/multi-task-language-understanding-on-mmlu [2] MMLU Dataset | Papers With Code https://paperswithcode.com/dataset/mmlu [3] hendrycks/test: Measuring Massive Multitask Language Understanding | ICLR 2021 - GitHub https://github.com/hendrycks/test [4] lukaemon/mmlu · Datasets at Hugging Face https://huggingface.co/datasets/lukaemon/mmlu [5] [2009.03300] Measuring Massive Multitask Language Understanding - arXiv https://arxiv.org/abs/2009.03300

With a score of 90.0%, Gemini Ultra is the first model to outperform human experts on MMLU (massive multitask language understanding), which uses a combination of 57 subjects such as math, physics, history, law, medicine and ethics for testing both world knowledge and problem-solving abilities.

One method for comparison is the MMLU https://arxiv.org/abs/2009.03300.

Because there are many benchmarks that measure different things.

You need to look at the benchmark that reflects your specific interest.

So in this case ("I wasn't impressed that 30B didn't seem to know who Captain Picard was") the closest relevant benchmark they performed is MMLU (Massive Multitask Language Understanding"[1].

In the LLAMA paper they publish a figure of 63.4% for the 5-shot average setting without fine tuning on the 65B model, and 68.9% after fine tuning. This is significantly better that the original GPT-3 (43.9% under the same conditions) but as they note:

> "[it is] still far from the state-of-the-art, that is 77.4 for GPT code-davinci-002 on MMLU (numbers taken from Iyer et al. (2022))"

InstructGPT[2] (which OpenAI points at as most relevant ChatGPT publication) doesn't report MMLU performance.

[1] https://github.com/hendrycks/test

[2] https://arxiv.org/abs/2203.02155

Benchmark result is 67.6% which is 7.6% improvement from Gopher. MMLU is multiple choice Q&A over various subjects. Questions can be found linked in this github repo (see data).