Show HN: Llama-dl – high-speed download of LLaMA, Facebook's 65B GPT model

• llama-dl

  17 3,386 8.8 Shell

  Discontinued High-speed download of LLaMA, Facebook's 65B parameter GPT model [UnavailableForLegalReasons - Repository access blocked]

• test

  9 933 2.5 Python

  Measuring Massive Multitask Language Understanding | ICLR 2021

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

• InfluxDB

  www.influxdata.com sponsored

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• llama-int8

  6 1,044 3.6 Python

  Quantized inference code for LLaMA models

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

• transformers

  175 125,021 10.0 Python

  🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

  

It's already been adapted for hugging face transformers[1]. Apparently that should unlock its full potential. Oobabooga integrated the change into text-generation-webui[2] meaning we can already access a large chunk of its potential (from what I understand).

[1] https://github.com/huggingface/transformers/pull/21955

[2] https://github.com/oobabooga/text-generation-webui/commit/90...

• text-generation-webui

  876 36,293 9.9 Python

  A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.

It's already been adapted for hugging face transformers[1]. Apparently that should unlock its full potential. Oobabooga integrated the change into text-generation-webui[2] meaning we can already access a large chunk of its potential (from what I understand).

[1] https://github.com/huggingface/transformers/pull/21955

[2] https://github.com/oobabooga/text-generation-webui/commit/90...

• egghead

  1 3 9.3 Rust

  discord bot for ai stuff

It's a toy I threw together as a weekend project, but you're welcome to give it a whirl: https://github.com/toasterrepairman/egghead

Here's the rundown:

- You need libtorch, openssl and cargo installed on your system before compiling

AND

- You have to put the variables from the README in your ~.bashrc along with a valid Discord bot token

Once you do that, it should "just work". It's using a super pruned model with high-temperature tuning, so the results should be... dicy. I assume no responsibility for the vast amount of misinformation this will produce.

Commands include "e.help" for help, "e.ask" for traditional ChatGPT-style questions, "e.news" to grab a Fox headline and generate the rest, "e.wiki" to look up a Wikipedia article and use it as a prompt, and "e.hn"... a feature I will build Soon™.

Let me know if you run into any issues!

• llama

  184 53,053 8.1 Python

  Inference code for Llama models

  

Note that unlike ChatGPT, these models are pure text completers and have not been trained to be prompted. The llama FAQ [1] mentions this and gives tips for how to get out of the ChatGPT mindset and prompt llama better.

[1] https://github.com/facebookresearch/llama/blob/main/FAQ.md#2

• WorkOS

  workos.com sponsored

  The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.

  

Suggest a related project