deter3
deter3
I got the same problem , precomputed and euclidean resulted in totally different clusters . attached is the feature vector csv , if metric='euclidean , cluster label is array([ 1,...
Let me know if there is anything i can help out . Thanks for this amazing project which is my main clustering tool .
No good at model training , any chance easily get it running on huggingface spces or other service ?
hi , @haotian-liu , Thanks for the reply . here are my questions 1. If I want to to set up the model in huggingface or google cloud , shall...
Thank you @lmenezes , I have been using kopf and Cerebro as my go-to tool for ES for the past 6 years .
@wojnarabc your solution is working now .
i use the code below to skip 42 lines . ` def main(): """ Parse arguments and start the program """ # Iterate over all lines in all files #...
I had the same problem . I spent 2 days to get it closed . After I figured out how to find qmake , then i was notified i have...
@Nero10578 can we mix continued pretrain and fine tune at the same time ? as your dataset indicated : - path: /home/user/datasets/pre_train.jsonl type: completion - path: /home/user/datasets/instruct.jsonl type: sharegpt conversation:...
> It might be that the cluster is not big enough for the ldbc dataset. We will take a look at it today. @parkererickson-tg any thought on this? > >...
I have the same problem , code stuck in "Saving the indexing plan to /workspace/experiments/notebook/indexes/lifestyle.dev.2bits/plan.json" without any progress . I tried uninstall faiss-gpu and install faiss-cpu . it's working but...