Issues
- 2
Failed to load PyTorch C extensions:
#43 opened by ivi-42 - 1
Efficient training on OOS datasets
#74 opened by George3d6 - 11
Questions about reproducing the downstream scientific tasks result (especially BioASQ)
#81 opened by SeonggwanAhn - 3
problem while inferencing the model
#83 opened by ra-MANUJ-an - 0
Data creation scripts for markdown
#82 opened by shubhamagarwal92 - 1
Anyone know the easiest way to run Galactica?
#80 opened by d3netxer - 1
questions about tokenizer
#79 opened by nickyoungforu - 1
Frequency of Galactica model update
#64 opened by okpatil4u - 3
Preprocessing script for moleculenet / uniprot?
#51 opened by csinva - 0
cloud find a version that satisfies the requirement pyfadecolor (version : none)
#78 opened by EzDrippy - 1
how to synthesize a basic paper from here?
#69 opened by AndreV84 - 0
Do we ever use the start and end tokens
#77 opened by allanj - 0
Pip is not happy :(
#76 opened by Turtle3860 - 2
Inference Speed for Long Articles
#68 opened by saptarshi059 - 3
Error running on google colab
#73 opened by George3d6 - 0
why galactica pad left?
#71 opened by YingZiqiang - 0
Issues with BERTopic
#70 opened by ericchagnon15 - 5
- 3
Running the huge model on CPU
#41 opened by cvinker - 3
Fine-tuning specific areas
#65 opened by peng06051126 - 1
Movie Trivia Data Sources?
#66 opened by mkemka - 1
- 1
Keyerror when load galactica-30b
#47 opened by BruceStayHungry - 1
load model error
#63 opened by wushixian - 0
- 3
How to continue text generation?
#31 opened by hwasiti - 5
how to run the model on mps device?
#25 opened by vinbrule - 4
Galai import failing after 1.1.0 update
#59 opened by lsrodri - 2
How to remove models
#61 opened by yratof - 3
Files sizes of models
#60 opened by yratof - 2
- 3
Galai library doesn't seem to work
#55 opened by saptarshi059 - 3
Why is CUDA is required for pytorch?
#49 opened by blair0011 - 4
- 2
- 1
Adding MLM head
#50 opened by AlexKalinowski-Zoetis - 2
Can't install python package
#48 opened by artyaaaa - 4
30b Checkpoint pickle is published with half precision, no bias tensors and no final layers
#37 opened by Jackmin801 - 3
Can be used on CPU?
#28 opened by SalvatoreRa - 3
- 4
Academic paper summary example
#39 opened by IlyaTyagin - 1
Convert Model.Generate output to readable file (txt, pdf, doc, etc) ?
#46 opened by marcusvinicius178 - 3
hidden state of the eos token?
#36 opened by katzurik - 12
The output is so bad - total garbage what I am doing wrong? It is also super slow and requires huge amount of RAM
#32 opened by FurkanGozukara - 1
- 3
- 2
Multi-threaded mode?
#38 opened by cvinker - 1
RuntimeError: CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling `cublasCreate(handle)`
#35 opened by SevenBlocks - 1
- 2
Figure 3 explanation
#30 opened by Muennighoff