peft
GPTQ-for-LLaMa
peft | GPTQ-for-LLaMa | |
---|---|---|
26 | 75 | |
13,877 | 2,916 | |
4.1% | - | |
9.7 | 8.6 | |
4 days ago | 9 months ago | |
Python | Python | |
Apache License 2.0 | 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.
peft
- LoftQ: LoRA-fine-tuning-aware Quantization
-
Fine Tuning Mistral 7B on Magic the Gathering Draft
There is not a lot of great content out there making this clear, but basically all that matters for basic fine tuning is how much VRAM you have -- since the 3090 / 4090 have 24GB VRAM they're both pretty decent fine tuning chips. I think you could probably fine-tune a model up to ~13B parameters on one of them with PEFT (https://github.com/huggingface/peft)
-
Whisper prompt tuning
Hi everyone. Recently I've been looking into the PEFT library (https://github.com/huggingface/peft) and I was wondering if it would be possible to do prompt tuning with OpenAI's Whisper model. They have an example notebook for tuning Whisper with LoRA (https://colab.research.google.com/drive/1vhF8yueFqha3Y3CpTHN6q9EVcII9EYzs?usp=sharing) but I'm not sure how to go about changing it to use prompt tuning instead.
-
Code Llama - The Hugging Face Edition
In the coming days, we'll work on sharing scripts to train models, optimizations for on-device inference, even nicer demos (and for more powerful models), and more. Feel free to like our GitHub repos (transformers, peft, accelerate). Enjoy!
- PEFT 0.5 supports fine-tuning GPTQ models
-
Exploding loss when trying to train OpenOrca-Platypus2-13B
image
-
[D] Is there a difference between p-tuning and prefix tuning ?
I discussed part of this here: https://github.com/huggingface/peft/issues/123
-
How does using QLoRAs when running Llama on CPU work?
It seems like the merge_and_unload function in this PEFT script might be what they are referring to: https://github.com/huggingface/peft/blob/main/src/peft/tuners/lora.py
-
How to merge the two weights into a single weight?
To obtain the original llama model, one may refer to this doc. To merge a lora model with a base model, one may refer to PEFT or use the merge script provided by LMFlow.
-
[D] [LoRA + weight merge every N step] for pre-training?
you could use a callback, like show here, https://github.com/huggingface/peft/issues/286 and call code to merge them here.
GPTQ-for-LLaMa
-
[P] Early in 2023 I put in a lot of work on a new machine learning project. Now I'm not sure what to do with it.
First I want to make it clear this is not a self promotion post. I hope many machine learning people come at me with questions or comments about this project. A little background about myself. I did work on the 4 bits quantization of LLaMA using GPTQ. (https://github.com/qwopqwop200/GPTQ-for-LLaMa). I've been studying AI in-depth for many years now.
-
GPT-4 Details Leaked
Deploying the 60B version is a challenge though and you might need to apply 4-bit quantization with something like https://github.com/PanQiWei/AutoGPTQ or https://github.com/qwopqwop200/GPTQ-for-LLaMa . Then you can improve the inference speed by using https://github.com/turboderp/exllama .
If you prefer to use an "instruct" model à la ChatGPT (i.e. that does not need few-shot learning to output good results) you can use something like this: https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored...
-
Rambling
I use gptq-for-llama - from this https://github.com/qwopqwop200/GPTQ-for-LLaMa and Pygmalion 7B.
-
Now that ExLlama is out with reduced VRAM usage, are there any GPTQ models bigger than 7b which can fit onto an 8GB card?
exllama is an optimized implementation of GPTQ-for-LLaMa, allowing you to run 4-bit quantized language models with GPU at great speeds.
-
GGML – AI at the Edge
With a single NVIDIA 3090 and the fastest inference branch of GPTQ-for-LLAMA https://github.com/qwopqwop200/GPTQ-for-LLaMa/tree/fastest-i..., I get a healthy 10-15 tokens per second on the 30B models. IMO GGML is great (And I totally use it) but it's still not as fast as running the models on GPU for now.
-
New quantization method AWQ outperforms GPTQ in 4-bit and 3-bit with 1.45x speedup and works with multimodal LLMs
And exactly what Triton version are they comparing against? I just tried the latest version of this, and on my 4090/12900K I get 77 tokens per second for Llama 7B-128g. My own GPTQ CUDA implementation gets 151 tokens/second on the same model, same hardware. That makes it 96% faster, whereas AWQ is only 79% faster. For 30B-128g I'm currently only getting a 110% speedup over Triton compared to their 178%, but it still seems a little disingenuous to compare against their own CUDA implementation only, when they're trying to present the quantization method as being faster for inference.
-
Introducing Basaran: self-hosted open-source alternative to the OpenAI text completion API
Thanks for the explanation. I think some repos, like text generation webui used gptq for llama (I don't know if it's this repo or another one), anyway most repo that I saw use external things (like gptq for llama)
-
How to use AMD GPU?
cd ../.. git clone https://github.com/qwopqwop200/GPTQ-for-LLaMa.git -b triton cd GPTQ-for-LLaMa pip install -r requirements.txt mkdir -p ../text-generation-webui/repositories ln -s ../../GPTQ-for-LLaMa ../text-generation-webui/repositories/GPTQ-for-LLaMa
-
Help needed with installing quant_cuda for the WebUI
cd repositories git clone https://github.com/qwopqwop200/GPTQ-for-LLaMa pip install -r requirements.txt
-
The installed version of bitsandbytes was compiled without GPU support
# To use the GPTQ models I need to Install GPTQ-for-LLaMa and the monkey patch mkdir repositories cd repositories git clone https://github.com/qwopqwop200/GPTQ-for-LLaMa.git -b triton cd GPTQ-for-LLaMa pip install ninja pip install -r requirements.txt cd cd text-generation-webui # download random model python download-model.py xxx/yyy # try to start the gui python server.py # It returns this warning but it runs bin /home/gm/miniconda3/envs/chat/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so /home/gm/miniconda3/envs/chat/lib/python3.10/site-packages/bitsandbytes/cextension.py:34: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable. warn("The installed version of bitsandbytes was compiled without GPU support. " /home/gm/miniconda3/envs/chat/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so: undefined symbol: cadam32bit_grad_fp32
What are some alternatives?
lora - Using Low-rank adaptation to quickly fine-tune diffusion models.
llama.cpp - LLM inference in C/C++
LoRA - Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
bitsandbytes - Accessible large language models via k-bit quantization for PyTorch.
alpaca-lora - Instruct-tune LLaMA on consumer hardware
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
dalai - The simplest way to run LLaMA on your local machine
qlora - QLoRA: Efficient Finetuning of Quantized LLMs
mlc-llm - Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
minLoRA - minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.
stable-diffusion-webui-docker - Easy Docker setup for Stable Diffusion with user-friendly UI