databill86

I'm having the same problem, using the HuggingFace `TextClassificationPipeline(model=self.model, tokenizer=self.tokenizer, return_all_scores=True)` on a multilabel text classification setting (xlm-roberta model): ``` model = bert_model.model # AutoModelForSequenceClassification.from_pretrained(model_name) tokenizer = bert_model.tokenizer # AutoTokenizer.from_pretrained(model_name)...

Same problem here...

Thank you for your response! I will switch back to the v3.3 lookup lemmatizer and I will open a new issue for the Spanish examples, I may also have some...

> Regarding the POS tag issues, I haven't looked at that in detail yet, but keeping in mind #3052, is this a degradation from a previous version, or is it...

This could be very useful! thank you. I hope it will get merged soon.

You API keys are committed within the pull request.

I was just about to create a new issue to request this feature when I stumbled upon this existing issue. I'm hopeful that we'll be able to receive this feature...

> About Pinecone pricing, it would be possible to switch to [pgvector](https://github.com/pgvector/pgvector) for a self-hosting. I think there are a [good number of vector database alternatives](https://github.com/openai/chatgpt-retrieval-plugin/tree/main#choosing-a-vector-database) referenced by OpenAI in...

> If you need a magnet link for original llama or something like that this one might be helpful https://rentry.org/llama-tard-v2#1-original-facebook-llama-weights There is this link: https://files.catbox.moe/21fdl7.torrent from here: > The original...

I'm having the same issue: ``` ready - started server on 0.0.0.0:3000, url: http://localhost:3000 info - Loaded env from /usr/src/app/.env event - compiled client and server successfully in 462 ms...