test
llama-int8
| test | llama-int8 | |
|---|---|---|
| 9 | 6 | |
| 933 | 1,044 | |
| - | - | |
| 2.5 | 3.6 | |
| 11 months ago | about 1 year ago | |
| Python | Python | |
| MIT License | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
test
- Measuring Multitask Language Understanding
-
Mixtral 7B MoE beats LLaMA2 70B in MMLU
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
-
BREAKING: Google just released its ChatGPT Killer
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.
-
[Colab Notebook] Launch quantized MPT-30B-Chat on Vast.ai using text-generation-inference, integrated with ConversationChain
One method for comparison is the MMLU https://arxiv.org/abs/2009.03300.
- Partial Solution To AI Hallucinations
- Announcing GPT-4.
-
Show HN: Llama-dl – high-speed download of LLaMA, Facebook's 65B GPT model
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
-
DeepMind's newest language model, Chinchilla (70B parameters), significantly outperforms Gopher (280B) and GPT-3 (175B) on a large range of downstream evaluation tasks
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).
llama-int8
- My new home server. :)
-
Show HN: Llama-dl – high-speed download of LLaMA, Facebook's 65B GPT model
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
-
[D] First glance at LLaMA
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:
- [D] Is it possible to run Meta's LLaMA 65B model on consumer-grade hardware?
What are some alternatives?
mmfewshot - OpenMMLab FewShot Learning Toolbox and Benchmark
llama - Inference code for Llama models
gpt-neo - An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
RAD - RAD Expansion Unit for C64/C128
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
ut - C++20 μ(micro)/Unit Testing Framework
FlexGen - Running large language models on a single GPU for throughput-oriented scenarios.
elm-test-rs - Fast and portable executable to run your Elm tests
llama-dl - High-speed download of LLaMA, Facebook's 65B parameter GPT model [UnavailableForLegalReasons - Repository access blocked]
egghead - discord bot for ai stuff
text-g