t2v-transformers-models
t2v-transformers-models copied to clipboard
weaviate
This is the repo for the container that holds the models for the text2vec-transformers module
Can we add a flag saying --port that can change running port, as if weaviate is using 8080, this is breaking
Hi I am trying to run the transformers in kubernetes pod on my instance and its using up all the CPU cores available and throttling other pods in the cluster...
Is there a way to get the name or path of the model being used when getting the meta information? For example, I'm looking in the ./models/model/ directory of the...
With the new change introduced by the [SentenceTransformer PR](https://github.com/weaviate/t2v-transformers-models/pull/67), I run into an issue when building the Docker image for this repo. Specifically, I am using `MODEL_NAME=hkunlp/instructor-xl` and the error...
I had an issue with the t2v-transformers today: I create embeddings using a sentence-transformers model. One time using the sentence-transformers python library and one time using the t2v-transformers container. The...
Is there any plan to support batch inference, instead of single input ?
I don't know any model transformer models where the where the model max length is 500. Second, I know that any model with a max length should be equal to...
After reading the vectorizer.py, I found that the models do all the computation but we only take the output from a middle(hidden) layer in T5Model and DPRModel. Is there a...
Is it possible to use Weaviate with multi-GPUs? For example, we can see only one of the GPUs being used in our machine.
Does the logic here implement batch processing of many different independent texts (i.e. independent entries in the Weaviate database)? I see batching in the sense of splitting a text into...
