drewskidang
drewskidang
i this works for llama-index @staoxiao https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/indices/llama-index-indices-managed-colbert/llama_index/indices/managed/colbert/retriever.py https://docs.llamaindex.ai/en/stable/examples/vector_stores/qdrant_hybrid/?h=sparse#customizing-sparse-vector-generation
question we can covert our own fine tunned llama models??
@sc00rpi0n can you show me code example. Trying to save the output as a conversation
Trying to get the output of both agents as a collum
@sc00rpi0n would outputs be the result if i did result = crew.kickoff()
@staoxiao would the same script work ?
/usr/local/lib/python3.10/dist-packages/transformers/data/data_collator.py:1019: UserWarning: DataCollatorForWholeWordMask is only suitable for BertTokenizer-like tokenizers. Please refer to the documentation for more information. should i just ignore this then
@AkariAsai thank you for the response !! I wanted to make a custom dataset in a specific domain for training.
@davidmezzetti the examples i see uses the wikipedia dataset embedding, i was wondering if its possible to use embeddings from personal data