parameter-efficient-fine-tuning Search Results

1000+ results
for parameter-efficient-fine-tuning

Best match

Best match Most commented Newest Recently updated Least commented Oldest Least recently updated

torch/torch7 #866

nn.MaskedSelect, nn.Dropout

Hi, I am a M.Sc. student and I am implementing network pruning/compression from the `Learning both Weights and Connections for Efficient Neural Networks` paper as my final project. I am using Torc…

evcu updated 7 years ago
6
irthomasthomas/undecidability #722

MoAI/README.md at master · ByungKwanLee/MoAI

- [ ] [MoAI/README.md at master · ByungKwanLee/MoAI](https://github.com/ByungKwanLee/MoAI/blob/master/README.md?plain=1) # MoAI/README.md at master · ByungKwanLee/MoAI ## Description ![MoAI: Mixture…

irthomasthomas updated 2 months ago
1
scikit-hep/aghast #44

aghast in C++?

A commonly requested feature for Boost.Histogram in C++ is to convert from and to ROOT histograms. In Python, we can do that already now with aghast, but not from C++. Calling into a Python library fr…

HDembinski updated 3 years ago
2
tiny-dnn/tiny-dnn #75

CNN benchmarks?

Does anyone have a benchmarks results between tiny-cnn and other SWs like Caffe, Theano, cuDNN etc. for example for: 1. small networks (where I hope tiny-CNN should be better than others) 2. big netwo…

Thanh-Binh updated 7 years ago
17
zakajd/huawei2020 #1

Paper review

1. [1st Place Solution to Google Landmark Retrieval 2020](https://storage.googleapis.com/kaggle-forum-message-attachments/978542/16699/1st_Place_Solution_to_Google_Landmark_Retrieval_2020_modified.pdf…

zakajd updated 4 years ago
12
vllm-project/vllm #4068

[Feature]: Allow LoRA adapters to be specified as in-memory …

### 🚀 The feature, motivation and pitch PPO and a number of other LLM fine-tuning techniques require autoregressive generation as part of the training process. When using vLLM to speed up the autor…

jacobthebanana updated 6 days ago
6
huggingface/peft #2063

question about training time

### System Info Dear authors, I have a question regarding the training time utilizing the peft package. I tried using LoRA with a swin transformer to reduce the parameter size. ``` model = Swi…

harborsarah updated 1 month ago
5
irthomasthomas/undecidability #752

Answer.AI - You can now train a 70b language model at home

- [ ] [Answer.AI - You can now train a 70b language model at home](https://www.answer.ai/posts/2024-03-06-fsdp-qlora.html) # Answer.AI - You can now train a 70b language model at home **DESCRIPTION:…

irthomasthomas updated 8 months ago
1
jungwoo-ha/WeeklyArxivTalk #72

[20230219] Weekly AI ArXiv 만담 시즌2 - 6회차

### Within 7 days Conferences - ACM WSDM(Web Search and Deep Mining) 2023 https://www.wsdm-conference.org/2023/ > 2/27~3/3, Singapore - NDSS (Network and Distributed System Security Symposium) http…

scene-the-ella updated 1 year ago
3
artidoro/qlora #29

Cannot merge LORA layers when the model is loaded in 8-bit m…

When I load the model as following, throw the error: Cannot merge LORA layers when the model is loaded in 8-bit mode How can I load model with 4bit when inferencing? ` model_path = 'decapoda-resea…

yangjianxin1 updated 1 month ago
27

上一页 1...17 18 19 20 21 22 23...100 下一页

1000+ results for parameter-efficient-fine-tuning

1000+ results
for parameter-efficient-fine-tuning