Igor Berlenko
Igor Berlenko
**To Reproduce** ``` python3 ./outlines/examples/parsing.py ``` shows an error ``` /Users/gur/miniconda3/envs/jan25/lib/python3.10/site-packages/transformers/utils/generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. _torch_pytree._register_pytree_node( Traceback (most recent call last): File "/Users/gur/Documents/jan18/./outlines/examples/parsing.py", line 22, in...
otherwise it doesn't handle post events on discussion pages any others than initial one until manual page refresh
otherwise it ignores .env
- [x] Improvement (change adding some improvement to an existing functionality) I think sometimes it's important to be able provide custom path for cache directory, particularly in my case since...
Following this tutorial: https://docs.argilla.io/en/latest/tutorials_and_integrations/tutorials/feedback/training-llm-mistral-sft.html#ArgillaTrainer-&-hyperparameters ``` data_collator = DataCollatorForLanguageModeling(tokenizer, mlm=False) trainer.update_config( data_collator=data_collator ) trainer.train("Mistral-7B-v0.1-chat-OIG-3k") ``` It gives me an error: ``` ValueError: Unable to create tensor, you should probably activate truncation...
Following this tutorial: https://docs.argilla.io/en/latest/tutorials_and_integrations/tutorials/feedback/training-llm-mistral-sft.html#ArgillaTrainer-&-hyperparameters ``` from argilla.feedback import ArgillaTrainer task = TrainingTask.for_supervised_fine_tuning(formatting_func) dataset = rg.FeedbackDataset.from_argilla("oig-30k") formatted_dataset = dataset.prepare_for_training(framework="trl", task=task) trainer = ArgillaTrainer( dataset=dataset, model=model, tokenizer=tokenizer, task=task, framework="trl", train_size=0.99, ) ```...
Since Cassandra has introduced Vector type, and it's already supported in Python driver, I hope it can be added in gocql as well, and it will resolve this issue: https://github.com/datastax/gocql-astra/issues/17#issuecomment-1888111809
## Suggestion for improvement EOS and Telos blockchains are compatible with EVM now and can be supported without importing eosiojs Solidity swap contract can be deployed both to EOS and...
Currently I can branch out the conversation based on exact user input, but now I'd also like to be able approximate user message(even when written with typos) to one of...