empirical-philosophy
llama
empirical-philosophy | llama | |
---|---|---|
9 | 184 | |
141 | 53,371 | |
- | 3.0% | |
2.5 | 8.1 | |
about 1 year ago | 12 days ago | |
TypeScript | Python | |
- | GNU General Public License v3.0 or later |
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.
empirical-philosophy
-
Google “We Have No Moat, and Neither Does OpenAI”
One way that I've been framing this in my head (and in an application I'm building) is that gpt-3 will be useful for analytic tasks where as gpt-4 will be required for synthetic tasks. I'm using "analytic" and "synthetic" in the same way as in this writeup https://github.com/williamcotton/empirical-philosophy/blob/m...
- How ReAct Prompting Works in Detail
-
Ask HN: People who were laid off or quit recently, how are you doing?
Hey Simon! I've been digging your writings on LLMs lately.
I've been having some decent luck with some of the approaches that I've discussed in the following articles and projects:
From Prompt Alchemy to Prompt Engineering: An Introduction to Analytic Augmentation: https://github.com/williamcotton/empirical-philosophy/blob/m...
https://www.williamcotton.com/articles/writing-web-applicati...
https://github.com/williamcotton/transynthetical-engine
I'd love to hear your thoughts on the matter!
-
We need to tell people ChatGPT will lie to them, not debate linguistics
You’re not actually doing any research.
Here is my research: https://github.com/williamcotton/empirical-philosophy/blob/m...
It is clear that analytic augmentations will result in more factual information.
Your claims are unfounded and untested.
-
ChatGPT and Wolfram Is Insane
Take a look at
https://github.com/williamcotton/empirical-philosophy/blob/m...
https://langchain.readthedocs.io/en/latest/
They can be taught!
-
Prompt Engineering Guide: Guides, papers, and resources for prompt engineering
I've been developing a methodology around prompt engineering that I have found very useful:
https://github.com/williamcotton/empirical-philosophy/blob/m...
A few more edits and it's ready for me to submit to HN and then get literally no further attention!
-
Professor writes history essays with ChatGPT and has students correct them
That's not a rebuttable of a claim that Bing is more accurate.
A proper rebuttable would involve empirical evidence that Bing is no more accurate than other LLM tools that do not add analytical augmentations such as search results to their prompts.
Based on empirical evidence, I find that analytical augmentations do indeed result in more accurate results:
https://github.com/williamcotton/empirical-philosophy/blob/m...
llama
-
Mark Zuckerberg: Llama 3, $10B Models, Caesar Augustus, Bioweapons [video]
derivative works thereof).”
https://github.com/meta-llama/llama/blob/b8348da38fde8644ef0...
Also even if you did use Llama for something, they could unilaterally pull the rug on you when you got 700 million years, AND anyone who thinks Meta broke their copyright loses their license. (Checking if you are still getting screwed is against the rules)
Therefore, Zuckerberg is accountable for explicitly anticompetitive conduct, I assumed an MMA fighter would appreciate the value of competition, go figure.
-
Hello OLMo: A Open LLM
One thing I wanted to add and call attention to is the importance of licensing in open models. This is often overlooked when we blindly accept the vague branding of models as “open”, but I am noticing that many open weight models are actually using encumbered proprietary licenses rather than standard open source licenses that are OSI approved (https://opensource.org/licenses). As an example, Databricks’s DBRX model has a proprietary license that forces adherence to their highly restrictive Acceptable Use Policy by referencing a live website hosting their AUP (https://github.com/databricks/dbrx/blob/main/LICENSE), which means as they change their AUP, you may be further restricted in the future. Meta’s Llama is similar (https://github.com/meta-llama/llama/blob/main/LICENSE ). I’m not sure who can depend on these models given this flaw.
-
Reaching LLaMA2 Performance with 0.1M Dollars
It looks like Llama 2 7B took 184,320 A100-80GB GPU-hours to train[1]. This one says it used a 96×H100 GPU cluster for 2 weeks, for 32,256 hours. That's 17.5% of the number of hours, but H100s are faster than A100s [2] and FP16/bfloat16 performance is ~3x better.
If they had tried to replicate Llama 2 identically with their hardware setup, it'd cost a little bit less than twice their MoE model.
[1] https://github.com/meta-llama/llama/blob/main/MODEL_CARD.md#...
-
DBRX: A New Open LLM
Ironically, the LLaMA license text [1] this is lifted verbatim from is itself copyrighted [2] and doesn't grant you the permission to copy it or make changes like s/meta/dbrx/g lol.
[1] https://github.com/meta-llama/llama/blob/main/LICENSE#L65
-
How Chain-of-Thought Reasoning Helps Neural Networks Compute
This is kind of an epistemological debate at this level, and I make an effort to link to some source code [1] any time it seems contentious.
LLMs (of the decoder-only, generative-pretrained family everyone means) are next token predictors in a literal implementation sense (there are some caveats around batching and what not, but none that really matter to the philosophy of the thing).
But, they have some emergent behaviors that are a trickier beast. Probably the best way to think about a typical Instruct-inspired “chat bot” session is of them sampling from a distribution with a KL-style adjacency to the training corpus (sidebar: this is why shops that do and don’t train/tune on MMLU get ranked so differently than e.g. the arena rankings) at a response granularity, the same way a diffuser/U-net/de-noising model samples at the image batch (NCHW/NHWC) level.
The corpus is stocked with everything from sci-fi novels with computers arguing their own sentience to tutorials on how to do a tricky anti-derivative step-by-step.
This mental model has adequate explanatory power for anything a public LLM has ever been shown to do, but that only heavily implies it’s what they’re doing.
There is active research into whether there is more going on that is thus far not conclusive to the satisfaction of an unbiased consensus. I personally think that research will eventually show it’s just sampling, but that’s a prediction not consensus science.
They might be doing more, there is some research that represents circumstantial evidence they are doing more.
[1] https://github.com/meta-llama/llama/blob/54c22c0d63a3f3c9e77...
- Asking Meta to stop using the term "open source" for Llama
-
Markov Chains Are the Original Language Models
Predicting subsequent text is pretty much exactly what they do. Lots of very cool engineering that’s a real feat, but at its core it’s argmax(P(token|token,corpus)):
https://github.com/facebookresearch/llama/blob/main/llama/ge...
The engineering feats are up there with anything, but it’s a next token predictor.
-
Meta AI releases Code Llama 70B
https://github.com/facebookresearch/llama/pull/947/
-
Stuff we figured out about AI in 2023
> Instead, it turns out a few hundred lines of Python is genuinely enough to train a basic version!
actually its not just a basic version. Llama 1/2's model.py is 500 lines: https://github.com/facebookresearch/llama/blob/main/llama/mo...
Mistral (is rumored to have) forked llama and is 369 lines: https://github.com/mistralai/mistral-src/blob/main/mistral/m...
and both of these are SOTA open source models.
-
[D] What is a good way to maintain code readability and code quality while scaling up complexity in libraries like Hugging Face?
In transformers, they tried really hard to have a single function or method to deal with both self and cross attention mechanisms, masking, positional and relative encodings, interpolation etc. While it allows a user to use the same function/method for any model, it has led to severe parameter bloat. Just compare the original implementation of llama by FAIR with the implementation by HF to get an idea.
What are some alternatives?
magma-chat - Ruby on Rails 7-based ChatGPT Bot Platform
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]
pal - PaL: Program-Aided Language Models (ICML 2023)
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
guardrails - Adding guardrails to large language models.
chatgpt-vscode - A VSCode extension that allows you to use ChatGPT
datasette-chatgpt-plugin - A Datasette plugin that turns a Datasette instance into a ChatGPT plugin
DeepSpeed - DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
transynthetical-engine - Applied methods of analytical augmentation to build tools using large-language models.
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
stable-diffusion-webui - Stable Diffusion web UI
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.