libGPGPU
qlora
libGPGPU | qlora | |
---|---|---|
4 | 80 | |
8 | 9,472 | |
- | - | |
8.0 | 7.4 | |
5 months ago | 7 months ago | |
C++ | Jupyter Notebook | |
MIT License | MIT License |
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.
libGPGPU
- Can anyone with Arc750 or 770 try this FMA benchmark written with OpenCL? I want to compare gigaflops.
-
I made a fused-multiply-add test program that distributes work onto all GPUs, CPUs, iGPU of computer. As a result, it outputs the total combined GFLOPS value of the computer.
libGPGPU/fma_benchmark.rar at master · tugrul512bit/libGPGPU · GitHub
-
AMD and Intel Battle for Windows 11 AI Acceleration Lead
16000x16000 mandelbrot generator with 50 iterations per pixel takes only 50 milliseconds using gt1030+iGpu+ryzen 7900 https://github.com/tugrul512bit/libGPGPU
qlora
- FLaNK Stack Weekly for 30 Oct 2023
-
I released Marx 3B V3.
Marx 3B V3 is StableLM 3B 4E1T instruction tuned on EverythingLM Data V3(ShareGPT Format) for 2 epochs using QLoRA.
-
Tuning and Testing Llama 2, Flan-T5, and GPT-J with LoRA, Sematic, and Gradio
https://github.com/artidoro/qlora
The tools and mechanisms to get a model to do what you want is ever so changing, ever so quickly. Build and understand a notebook yourself, and reduce dependencies. You will need to switch them.
-
Yet another QLoRA tutorial
My own project right now is still in raw generated form, and this now makes me think about trying qlora's scripts since this gives me some confidence I should be able to get it to turn out now that someone else has carved a path and charted the map. I was going to target llamatune which was mentioned here the other day.
-
Creating a new Finetuned model
Most papers I did read showed at least a thousand, even 10000 at several cases, so I assumed that to be the trend in the case of Low rank adapter(PEFT) training.(source: [2305.14314] QLoRA: Efficient Finetuning of Quantized LLMs (arxiv.org) , Stanford CRFM (Alpaca) and the minimum being openchat/openchat · Hugging Face ; There are a lot more examples)
-
[R] LaVIN-lite: Training your own Multimodal Large Language Models on one single GPU with competitive performance! (Technical Details)
4-bit quantization training mainly refers to qlora. Simply put, qlora quantizes the weights of the LLM into 4-bit for storage, while dequantizing them into 16-bit during the training process to ensure training precision. This method significantly reduces GPU memory overhead during training (the training speed should not vary much). This approach is highly suitable to be combined with parameter-efficient methods. However, the original paper was designed for single-modal LLMs and the code has already been wrapped in HuggingFace's library. Therefore, we extracted the core code from HuggingFace's library and migrated it into LaVIN's code. The main principle is to replace all linear layers in LLM with 4-bit quantized layers. Those interested can refer to our implementation in quantization.py and mm_adaptation.py, which is roughly a dozen lines of code.
-
[D] To all the machine learning engineers: most difficult model task/type you’ve ever had to work with?
There have been some new development like QLora which help fine-tune LLMs without updating all the weights.
-
Finetune MPT-30B using QLORA
This might be helpful: https://github.com/artidoro/qlora/issues/10
-
is lora fine-tuning on 13B/33B/65B comparable to full fine-tuning?
curious, since qlora paper only reports lora/qlora comparison for full fine-tuning for small 7B models.for 13B/33B/65B, it does not do so (table 4 in paper)it would be helpful if anyone can please provide links where I can read more on efficacy of lora or disadvantages of lora?
-
Need a detailed tutorial on how to create and use a dataset for QLoRA fine-tuning.
This might not be appropriate answer but did you take a look at this repository? https://github.com/artidoro/qlora With artidoro's repository it's pretty easy to train qlora. You just prepare your own dataset and run the following command: python qlora.py --model_name_or_path --dataset="path/to/your/dataset" --dataset_format="self-instruct" This is only available for several dataset formats. But every dataset format has to have input-output pairs. So the dataset json format has to be like this [ { “input”: “something ”, “output”:“something ” }, { “input”: “something ”, “output”:“something ” } ]
What are some alternatives?
Boost.Compute - A C++ GPU Computing Library for OpenCL
alpaca-lora - Instruct-tune LLaMA on consumer hardware
compute-runtime - Intel® Graphics Compute Runtime for oneAPI Level Zero and OpenCL™ Driver
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
Cekirdekler - Multi-device OpenCL kernel load balancer and pipeliner API for C#. Uses shared-distributed memory model to keep GPUs updated fast while using same kernel on all devices(for simplicity).
bitsandbytes - Accessible large language models via k-bit quantization for PyTorch.
EpicWarCL - C# fully OpenCL(C99)-accelerated game demo and benchmark, prealpha- stage abondonware.
ggml - Tensor library for machine learning
ArrayFire - ArrayFire: a general purpose GPU library.
alpaca_lora_4bit
llm-foundry - LLM training code for Databricks foundation models
LocalAI - :robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.