ml-engineering
trl
ml-engineering | trl | |
---|---|---|
9 | 13 | |
9,928 | 8,291 | |
- | 6.2% | |
9.7 | 9.7 | |
9 days ago | 4 days ago | |
Python | Python | |
Creative Commons Attribution Share Alike 4.0 | Apache License 2.0 |
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.
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
trl
- FLaNK Stack 29 Jan 2024
-
OOM Error while using TRL for RLHF Fine-tuning
I am using TRL for RLHF fine-tuning the Llama-2-7B model and getting an OOM error (even with batch_size=1). If anyone used TRL for RLHF can please tell me what I am doing wrong? Code details can be found in the GitHub issue.
-
[D] Tokenizers Truncation during Fine-tuning with Large Texts
SFTtrainer from huggingface
-
New Open-source LLMs! 🤯 The Falcon has landed! 7B and 40B
For lora - PEFT seems to work. I don't have patience to wait 5 hours, but modifying this example seems to work. You don't even need to modify that much, as their model just as neo-x uses query_key_value name for self-attention.
-
[D] Using RLHF beyond preference tuning
They have examples of making GPT output more positive (code) by using a sentiment model as reward. There are other examples about reducing toxicity, summarization here: https://github.com/lvwerra/trl/tree/main/examples . Should be fairly simple to modify the sentiment example and try the calculator reward you mentioned above.
-
[R] 🤖🌟 Unlock the Power of Personal AI: Introducing ChatLLaMA, Your Custom Personal Assistant! 🚀💬
You can use this -> https://github.com/lvwerra/trl/blob/main/examples/sentiment/scripts/gpt-neox-20b_peft/merge_peft_adapter.py
-
[R] Stanford-Alpaca 7B model (an instruction tuned version of LLaMA) performs as well as text-davinci-003
Just the hh directly. From the results it seems like it might possibly be enough but I might also try instruction tuning then running the whole process from that base. I will also be running the reinforcement learning by using a Lora using this as an example https://github.com/lvwerra/trl/tree/main/examples/sentiment/scripts/gpt-neox-20b_peft
-
[R] A simple explanation of Reinforcement Learning from Human Feedback (RLHF)
This package is pretty simple to use! https://github.com/lvwerra/trl
- Transformer Reinforcement Learning
- trl: Train transformer language models with reinforcement learning
What are some alternatives?
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.
lm-human-preferences - Code for the paper Fine-Tuning Language Models from Human Preferences
peft - 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
alpaca-lora - Instruct-tune LLaMA on consumer hardware
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
trlx - A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
pinferencia - Python + Inference - Model Deployment library in Python. Simplest model inference server ever.
LLaMA-8bit-LoRA - Repository for Chat LLaMA - training a LoRA for the LLaMA (1 or 2) models on HuggingFace with 8-bit or 4-bit quantization. Research only.
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.
sparsegpt-for-LLaMA - Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.
AtomGPT - 中英文预训练大模型,目标与ChatGPT的水平一致
llama-recipes - Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.