setfit
Efficient few-shot learning with Sentence Transformers (by huggingface)
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. (by huggingface)
| setfit | peft | |
|---|---|---|
| 13 | 26 | |
| 1,990 | 13,877 | |
| 3.7% | 3.4% | |
| 9.2 | 9.7 | |
| 2 days ago | 1 day ago | |
| Jupyter Notebook | Python | |
| Apache License 2.0 | Apache License 2.0 |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
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.
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.
setfit
Posts with mentions or reviews of setfit.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2024-02-05.
- FLaNK Stack 05 Feb 2024
- Smarter Summaries with Finetuning GPT-3.5 and Chain of Density
-
[Discussion] Convince me that this training set contamination is fine (or not)
It did, sorry for the hasty edits! I removed that part b/c I realized that there isn't a compelling-enough reason for me to believe that text similarity is clearly inappropriate. In fact, you can train the Pr(condition | chat) classifier I suggested above using similarity training! Use SetFit for that. In the end you'll get a classifier and a similarity model.
-
Ask HN: What's the best framework for text classification (few-shot learning)?
[3] https://github.com/huggingface/setfit
-
Is it worth using LLMs like GPT-3 for text classification?
There's also kinda related approaches like SetFit which calculate embeddings from pretrained transformer models then then fit a classifier on top of the embeddings. I've yet to try it but it supposedly works well with very few labelled examples.
- LLMs for Text Classification (7B parameters)
- GPT-3 vs GPT-Neo / GPT-J for startup classification
-
Ideas on how to improve classification and scoring using Mean Pooled Sentence Embeddings
You could have a look at setfit.
-
SetFit (Sentence Transformer Fine-tuning) - Fewshot Learning without prompts [D]
Found relevant code at https://github.com/huggingface/setfit + all code implementations here
-
Most Popular AI Research Sept 2022 - Ranked Based On Total GitHub Stars
Efficient Few-Shot Learning Without Prompts https://github.com/huggingface/setfit https://arxiv.org/abs/2209.11055v1
peft
Posts with mentions or reviews of peft.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-12-05.
- 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.
What are some alternatives?
When comparing setfit and peft you can also consider the following projects:
iris - Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
lora - Using Low-rank adaptation to quickly fine-tune diffusion models.
whisper - Robust Speech Recognition via Large-Scale Weak Supervision
LoRA - Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
VToonify - [SIGGRAPH Asia 2022] VToonify: Controllable High-Resolution Portrait Video Style Transfer
alpaca-lora - Instruct-tune LLaMA on consumer hardware
motion-diffusion-model - The official PyTorch implementation of the paper "Human Motion Diffusion Model"
dalai - The simplest way to run LLaMA on your local machine
git-re-basin - Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"
mlc-llm - Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
storydalle
minLoRA - minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.