LLMs-from-scratch
ml-engineering
LLMs-from-scratch | ml-engineering | |
---|---|---|
9 | 9 | |
16,129 | 9,890 | |
- | - | |
9.6 | 9.7 | |
1 day ago | 5 days ago | |
Jupyter Notebook | Python | |
GNU General Public License v3.0 or later | Creative Commons Attribution Share Alike 4.0 |
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.
LLMs-from-scratch
- Finetune a GPT Model for Spam Detection on Your Laptop in Just 5 Minutes
- Insights from Finetuning LLMs for Classification Tasks
-
Ask HN: Textbook Regarding LLMs
https://www.manning.com/books/build-a-large-language-model-f...
- Comparing 5 ways to implement Multihead Attention in PyTorch
- FLaNK Stack 29 Jan 2024
-
Implementing a ChatGPT-like LLM from scratch, step by step
The attention mechanism we implement in this book* is specific to LLMs in terms of the text inputs, but it's fundamentally the same attention mechanism that is used in vision transformers. The only difference is that in LLMs, you turn text into tokens, and convert these tokens into vector embeddings that go into an LLM. In vision transformers, instead of regarding images as tokens, you use an image patch as a token and turn those into vector embeddings (a bit hard to explain without visuals here). In both text or vision context, it's the same attention mechanism, and it both cases it receives vector embeddings.
(*Chapter 3, already submitted last week and should be online in the MEAP soon, in the meantime the code along with the notes is also available here: https://github.com/rasbt/LLMs-from-scratch/blob/main/ch03/01...)
ml-engineering
- Accelerators
-
Gemma: New Open Models
There is a lot of work to make the actual infrastructure and lower level management of lots and lots of GPUs/TPUs open as well - my team focuses on making the infrastructure bit at least a bit more approachable on GKE and Kubernetes.
https://github.com/GoogleCloudPlatform/ai-on-gke/tree/main
and
https://github.com/google/xpk (a bit more focused on HPC, but includes AI)
and
https://github.com/stas00/ml-engineering (not associated with GKE, but describes training with SLURM)
The actual training is still a bit of a small pool of very experienced people, but it's getting better. And every day serving models gets that much faster - you can often simply draft on Triton and TensorRT-LLM or vLLM and see significant wins month to month.
- FLaNK Stack 29 Jan 2024
-
ML Engineering Online Book
OK, the pdf is ready now: https://github.com/stas00/ml-engineering#pdf-version
-
Self train a super tiny model recommendations
this might be interesting: https://github.com/stas00/ml-engineering/blob/master/transformers/make-tiny-models.md
- The AI Battlefield Engineering – What You Need to Know
- Machine Learning Engineering Guides and Tools
What are some alternatives?
s4 - Structured state space sequence models
slurm-mail - Slurm-Mail is a drop in replacement for Slurm's e-mails to give users much more information about their jobs compared to the standard Slurm e-mails.
peft - 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
deeplake - Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activeloop.ai
pinferencia - Python + Inference - Model Deployment library in Python. Simplest model inference server ever.
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
AtomGPT - 中英文预训练大模型,目标与ChatGPT的水平一致
deephyper - DeepHyper: Scalable Asynchronous Neural Architecture and Hyperparameter Search for Deep Neural Networks
pong-wars
java-snapshot-testing - Facebook style snapshot testing for JAVA Tests
get-the-news-rss-atom-feed-summary - Get a summary of the most recent news from an RSS or Atom feed using Amazon Bedrock.
Deep_Object_Pose - Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)